NeuroAI for AI Safety
Abstract
As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions that deviate significantly from prior experiences, explore the world safely, understand pragmatics, and can cooperate to meet their intrinsic goals. Intelligence, when coupled with cooperation and safety mechanisms, can drive sustained progress and well-being. These properties are a function of the architecture of the brain and the learning algorithms it implements. Neuroscience may thus hold important keys to technical AI safety that are currently underexplored and underutilized. In this roadmap, we highlight and critically evaluate several paths toward AI safety inspired by neuroscience: emulating the brain’s representations, information processing, and architecture; building robust sensory and motor systems from imitating brain data and bodies; fine-tuning AI systems on brain data; advancing interpretability using neuroscience methods; and scaling up cognitively-inspired architectures. We make several concrete recommendations for how neuroscience can positively impact AI safety.
Appendix
Log-sigmoid scaling laws
We were surprised to find log-sigmoid scaling curves for digital in both empirical data and simulations; to the best of our knowledge, this has not been reported in the literature. We thus searched for a regime where a log-sigmoid scaling law follows naturally from asymptotics.
Consider a linear regression model–similar to the LNP model considered in the main text (Section 10.1), but more analytically tractable: \[y = X w + \epsilon\] where:
\(X \in \mathbb{R}^{N \times M}\) with entries \(X_{ij} \sim \mathcal{N}(0, 1)\).
\(w \sim \mathcal{N}\left(0, \frac{1}{M} I_M\right)\).
\(\epsilon \sim \mathcal{N}\left(0, \sigma_N^2 I_N\right)\).
The validation data \(X_{\text{val}} \in \mathbb{R}^{N_{\text{val}} \times M}\) with entries \(X_{\text{val}, ij} \sim \mathcal{N}(0, 1)\).
Note that with this definition, \(\text{var}(y) = 1 + \sigma_N^2\). We use a Maximum A Posteriori (MAP) estimate of \(w\) with a prior matching its sampling distribution: \[w_{\text{MAP}} = \left( X^\top X + M \sigma_N^2 I_M \right)^{-1} X^\top y\]
The Fraction of Explained Variance Estimator (FEVE) on the validation set is defined as: \[\text{FEVE} = 1 - \frac{\mathbb{E}\left[ \left( y_{\text{val}} - X_{\text{val}} w_{\text{MAP}} \right)^2 \right] - \sigma_N^2}{\mathbb{E}\left[ y_{\text{val}}^2 \right] - \sigma_N^2}\] where \(y_{\text{val}} = X_{\text{val}} w + \epsilon_{\text{val}}\).
Equivalently, the FEVE is the \(R^2\) on the validation set if there’s no noise in the validation set.
The denominator of FEVE is: \[\mathbb{E}\left[ y_{\text{val}}^2 \right] - \sigma_N^2 = 1\]
Similarly, the numerator is:
\[\mathbb{E}\left[ \left( X_{\text{val}} \left( w - w_{\text{MAP}} \right) \right)^2 \right]\]
Approximating \(X_{\text{val}}^\top X_{\text{val}} \approx N_{\text{val}} I_M\) (since entries are i.i.d. standard normal), the design matrix falls out, and we find that the numerator is:
\[\approx \mathbb{E}\left[ \left\| w - w_{\text{MAP}} \right\|^2 \right]\]
The posterior covariance matrix is: \[\Sigma_{\text{post}} = \left( X^\top X + M \sigma_N^2 I_M \right)^{-1} M \sigma_N^2 I_M\] Again using the expected value of the covariance matrix, we find that: \[\Sigma_{\text{post}} \approx \left( N I_M + M \sigma_N^2 I_M \right)^{-1} M \sigma_N^2 I_M = \frac{M \sigma_N^2}{N + M \sigma_N^2} I_M\] Therefore: \[\mathbb{E}\left[ \left\| w - w_{\text{MAP}} \right\|^2 \right] = \operatorname{Tr}\left( \Sigma_{\text{post}} \right) = \frac{M^2 \sigma_N^2}{N + M \sigma_N^2}\]
Finally, the FEVE is: \[\text{FEVE} \approx \frac{ N }{ N + M \sigma_N^2 }\]
We note that this can be expressed as the log sigmoid:
\[\text{FEVE} = \sigma(\log(N) - \log(M) - \log(\sigma^2_N))\]
Thus, under the assumptions we use, the scaling law for linear regression is a log-sigmoid. We note that our expression is valid when \(M > N\) and potentially high noise, the so-called classic regime. By contrast, Canatar et al. (2023) [113] tackle a different regime where there are far more regressors than observations, \(N > M\), and no noise, the so-called modern or interpolation regime.
We believe that the scenario we consider is a better reflection of practices in digital twins, as opposed as the analysis in [113], which better reflects practices in comparing neural networks and brains with task-driven neural networks. Neural data is noisy, and in the limit of high observation noise, we don’t always get better fits in the interpolation regime. It is common for digital twins to be fit in the classic regime; for example, Lurz et al. (2021) [87] have fewer than a hundred parameters in their readout, but thousands of observations. Future work should address how these two frameworks can be merged to cover the full range of scenarios in which digital twins and task-driven neural networks are fit.
[1] Mnih, V., K. Kavukcuoglu, D. Silver, et al., “Playing
atari with deep reinforcement learning”, arXiv
[cs.LG], 2013.
[2] Silver, D., A. Huang, C.J. Maddison, et al., “Mastering
the game of go with deep neural networks and tree search”,
Nature 529(7587), 2016, pp. 484–489.
[3] Silver, D., T. Hubert, J. Schrittwieser, et al., “A
general reinforcement learning algorithm that masters chess,
shogi, and go through self-play”, Science
362(6419), 2018, pp. 1140–1144.
[4] Krizhevsky, A., I. Sutskever, and G.E. Hinton,
“ImageNet classification with deep
convolutional neural networks”, Advances in neural
information processing systems, Curran Associates, Inc.
(2012).
[5] Dosovitskiy, A., L. Beyer, A. Kolesnikov, et al., “An
image is worth 16x16 words: Transformers for image
recognition at scale”, 2020.
[6] Grigorescu, S., B. Trasnea, T. Cocias, and G. Macesanu,
“A survey of deep learning techniques for autonomous
driving”, arXiv [cs.LG], 2019.
[7] Rajpurkar, P., E. Chen, O. Banerjee, and E.J. Topol,
“AI in health and medicine”, Nat.
Med. 28(1), 2022, pp. 31–38.
[8] Jumper, J., R. Evans, A. Pritzel, et al., “Highly
accurate protein structure prediction with
AlphaFold”, Nature
596(7873), 2021, pp. 583–589.
[9] Watson, J.L., D. Juergens, N.R. Bennett, et al.,
“Broadly applicable and accurate protein design by
integrating structure prediction networks and diffusion generative
models”, 2022.
[10] Brown, T.B., B. Mann, N. Ryder, et al., “Language
models are few-shot learners”, 2020.
[11] Bubeck, S., V. Chandrasekaran, R. Eldan, et al.,
“Sparks of artificial general intelligence: Early
experiments with GPT-4”, 2023.
[12] Trinh, T.H., Y. Wu, Q.V. Le, H. He, and T. Luong,
“Solving olympiad geometry without human
demonstrations”, Nature 625(7995), 2024,
pp. 476–482.
[13] Lam, R., A. Sanchez-Gonzalez, M. Willson, et al.,
“Learning skillful medium-range global weather
forecasting”, Science 382(6677), 2023,
pp. 1416–1421.
[14] Kochkov, D., J. Yuval, I. Langmore, et al., “Neural
general circulation models for weather and climate”,
Nature 632(8027), 2024, pp. 1060–1066.
[15] Pyzer-Knapp, E.O., J.W. Pitera, P.W.J. Staar, et al.,
“Accelerating materials discovery using artificial
intelligence, high performance computing and robotics”,
Npj Comput. Mater. 8(1), 2022, pp. 1–9.
[16] Rolnick, D., P.L. Donti, L.H. Kaack, et al., “Tackling
climate change with machine learning”, arXiv
[cs.CY], 2019.
[17] Luccioni, A.S., S. Viguier, and A.-L. Ligozat,
“Estimating the carbon footprint of BLOOM, a
176B parameter language model”, Journal of
Machine Learning Research, 2023, pp. 253:1–253:15.
[18] Zhang, B.H., B. Lemoine, and M. Mitchell, “Mitigating
unwanted biases with adversarial learning”, arXiv
[cs.LG], 2018.
[19] Bender, E.M., T. Gebru, A. McMillan-Major, and M. Mitchell,
“On the dangers of stochastic parrots: Can language models
be too big?”, Proceedings of the 2021 ACM conference on
fairness, accountability, and transparency, (2021).
[20] Peterson, D., and S. Hoffman, Geopolitical implications
of AI and digital surveillance adoption,
Brookings Institute, 2022.
[21] Urbina, F., F. Lentzos, C. Invernizzi, and S. Ekins,
“Dual use of artificial intelligence-powered drug
discovery”, Nat. Mach. Intell. 4(3),
2022, pp. 189–191.
[22] Bostrom, N., “Superintelligence: Paths, dangers,
strategies”, xvi 328, 2014.
[23] Amodei, D., C. Olah, J. Steinhardt, P. Christiano, J.
Schulman, and D. Mané, Concrete problems in AI
safety, arXiv, 2016.
[24] Bengio, Y., G. Hinton, A. Yao, et al., “Managing
extreme AI risks amid rapid progress”,
Science 384(6698), 2024, pp. 842–845.
[25] Bengio, Y., et al., Interim report, International
Scientific Report on the Safety of Advanced AI, 2024.
[26] Hendrycks, D., M. Mazeika, and T. Woodside, “An
overview of catastrophic AI risks”, 2023.
[27] Eloundou, T., S. Manning, P. Mishkin, and D. Rock,
“GPTs are GPTs: An early look at
the labor market impact potential of large language
models”, 2023.
[28] Ramesh, A., P. Dhariwal, A. Nichol, C. Chu, and M. Chen,
“Hierarchical text-conditional image generation with
CLIP latents”, arXiv [cs.CV], 2022.
[29] Christian, B., The alignment problem: Machine learning
and human values, WW Norton, New York, NY, 2021.
[30] Rapp, J.T., B.J. Bremer, and P.A. Romero, “Self-driving
laboratories to autonomously navigate the protein fitness
landscape”, Nat Chem Eng 1(1), 2024, pp.
97–107.
[31] Park, J.S., J.C. O’Brien, C.J. Cai, M.R. Morris, P. Liang,
and M.S. Bernstein, “Generative agents: Interactive
simulacra of human behavior”, arXiv [cs.HC], 2023.
[32] Lála, J., O. O’Donoghue, A. Shtedritski, S. Cox, S.G.
Rodriques, and A.D. White, “PaperQA:
Retrieval-augmented generative agent for scientific
research”, arXiv [cs.CL], 2023.
[33] Lu, C., C. Lu, R.T. Lange, J. Foerster, J. Clune, and D. Ha,
“The AI scientist: Towards fully automated
open-ended scientific discovery”, arXiv [cs.AI],
2024.
[34] Jimenez, C.E., J. Yang, A. Wettig, et al.,
“SWE-bench: Can language models resolve
real-world GitHub issues?”, arXiv
[cs.CL], 2023.
[35] Yang, J., C.E. Jimenez, A. Wettig, et al.,
“SWE-agent: Agent-computer interfaces enable
automated software engineering”, arXiv [cs.SE],
2024.
[36] Russell, S., Human compatible: Artificial intelligence
and the problem of control, Viking, 2019.
[37] Richards, B., B. Agüera y Arcas, G. Lajoie, and D. Sridhar,
“The illusion of AI’s
existential risk”, Noema, 2023.
[38] Cisek, P., “Evolution of behavioural control from
chordates to primates”, Phil. Trans. R. Soc. B
377(1844), 2022.
[39] Bennett, M., A brief history of intelligence,
Mariner Books, 2023.
[40] Ortega, P.A., V. Maini, and D.M.S. Team, “Building safe
artificial intelligence: Specification, robustness, and
assurance”, DeepMind Safety Research Blog, 2018.
[41] Geirhos, R., J.-H. Jacobsen, C. Michaelis, et al.,
“Shortcut learning in deep neural networks”, Nat
Mach Intell 2(11), 2020, pp. 665–673.
[42] Lindsay, G.W., and D. Bau, “Testing methods of neural
systems understanding”, Cogn. Syst. Res.
82, 2023, pp. 101156.
[43] Goodfellow, I.J., J. Shlens, and C. Szegedy,
“Explaining and harnessing adversarial examples”,
arXiv [stat.ML], 2014.
[44] Elsayed, G.F., S. Shankar, B. Cheung, et al.,
“Adversarial examples that fool both computer vision and
time-limited humans”, Neural Inf Process Syst
31, 2018, pp. 3914–3924.
[45] Ilyas, A., S. Santurkar, D. Tsipras, L. Engstrom, B. Tran,
and A. Madry, “Adversarial examples are not bugs, they are
features”, 2019.
[46] Guo, C., M.J. Lee, G. Leclerc, et al., “Adversarially
trained neural representations may already be as robust as
corresponding biological neural representations”, 2022.
[47] Bartoldson, B.R., J. Diffenderfer, K. Parasyris, and B.
Kailkhura, “Adversarial robustness limits via scaling-law
and human-alignment studies”, arXiv [cs.LG], 2024.
[48] Fort, S., and B. Lakshminarayanan, “Ensemble everything
everywhere: Multi-scale aggregation for adversarial
robustness”, arXiv [cs.CV], 2024.
[49] Li, Z., W. Brendel, E. Walker, et al., “Learning from
brains how to regularize machines”, Advances in neural
information processing systems, Curran Associates, Inc.
(2019).
[50] Dapello, J., T. Marques, M. Schrimpf, F. Geiger, D. Cox, and
J.J. DiCarlo, “Simulating a primary visual cortex at the
front of CNNs improves robustness to image
perturbations”, Advances in Neural Information
Processing Systems 33, 2020, pp. 13073–13087.
[51] Safarani, S., A. Nix, K. Willeke, et al., “Towards
robust vision by multi-task learning on monkey visual
cortex”, arXiv [cs.CV], 2021.
[52] Li, Z., J. Ortega Caro, E. Rusak, et al., “Robust deep
learning object recognition models rely on low frequency
information in natural images”, PLOS Computational
Biology 19(3), 2023, pp. e1010932.
[53] Marr, D., Vision: A computational approach, Freeman
& Co., San Francisco, 1982.
[54] Bostrom, N., and A. Sandberg, Whole brain emulation: A
roadmap, Future of Humanity Institute, 2008.
[55] Byrnes, S., “Intro to brain-like-AGI
safety”, 2022.
[56] Cvitkovic, M., “Neurotechnology is critical for
AI alignment”, 2023.
[57] Thiergart, L., and S.L. Norman, Distillation of neurotech
and alignment workshop january 2023, LessWrong, 2023.
[58] Olah, C., and S. Carter, “Research debt”,
Distill, 2017.
[59] Kahneman, D., Thinking, fast and slow, Farrar,
Straus & Giroux, New York, NY, 2013.
[60] Harari, Y.N., Sapiens: A brief history of humankind,
Harper, New York, NY, 2015.
[61] Descartes, R., Discourse on method, 1637.
[62] Zhuang, C., S. Yan, A. Nayebi, et al., “Unsupervised
neural network models of the ventral visual stream”,
Proc. Natl. Acad. Sci. U. S. A. 118(3), 2021.
[63] Nagarajan, V., A. Andreassen, and B. Neyshabur,
“Understanding the failure modes of out-of-distribution
generalization”, 2021.
[64] Lake, B.M., T.D. Ullman, J.B. Tenenbaum, and S.J. Gershman,
“Building machines that learn and think like people”,
Behav. Brain Sci. 40, 2017, pp. e253.
[65] Geirhos, R., P. Rubisch, C. Michaelis, M. Bethge, F.A.
Wichmann, and W. Brendel, “ImageNet-trained
CNNs are biased towards texture; increasing shape
bias improves accuracy and robustness”, arXiv.org,
2018.
[66] Wang, E.Y., P.G. Fahey, K. Ponder, et al., “Towards a
foundation model of the mouse visual cortex”, bioRxiv;
Accepted in Nature, 2024.
[67] Bashivan, P., K. Kar, and J.J. DiCarlo, “Neural
population control via deep image synthesis”,
Science 364(6439), 2019.
[68] Walker, E.Y., F.H. Sinz, E. Cobos, et al., “Inception
loops discover what excites neurons most using deep predictive
models”, Nat. Neurosci. 22(12), 2019, pp.
2060–2065.
[69] Gu, J., X. Jia, P. de Jorge, et al., “A survey on
transferability of adversarial examples across deep neural
networks”, arXiv [cs.CV], 2023.
[70] Brendel, W., J. Rauber, and M. Bethge, “Decision-based
adversarial attacks: Reliable attacks against black-box machine
learning models”, arXiv [stat.ML], 2017.
[71] Athalye, A., L. Engstrom, A. Ilyas, and K. Kwok,
“Synthesizing robust adversarial examples”, arXiv
[cs.CV], 2017.
[72] Howe, N., M. Zajac, I. McKenzie, et al., “Exploring
scaling trends in LLM robustness”, arXiv
[cs.LG], 2024.
[73] Wang, T.T., A. Gleave, T. Tseng, et al., “Adversarial
policies beat superhuman go AIs”, arXiv
[cs.LG], 2022.
[74] Gleave, A., “AI safety in a world of
vulnerable machine learning systems”, 2023.
[75] Zador, A.M., “A critique of pure learning and what
artificial neural networks can learn from animal brains”,
Nat. Commun. 10(1), 2019, pp. 1–7.
[76] Hasson, U., S.A. Nastase, and A. Goldstein, “Direct fit
to nature: An evolutionary perspective on biological and
artificial neural networks”, Neuron
105(3), 2020, pp. 416–434.
[77] Lake, B.M., R. Salakhutdinov, and J.B. Tenenbaum,
“Human-level concept learning through probabilistic program
induction”, Science 350(6266), 2015, pp.
1332–1338.
[78] Filos, A., P. Tigas, R. McAllister, N. Rhinehart, S. Levine,
and Y. Gal, “Can autonomous vehicles identify, recover from,
and adapt to distribution shifts?”, arXiv [cs.LG],
2020.
[79] Sucholutsky, I., L. Muttenthaler, A. Weller, et al.,
“Getting aligned on representational alignment”,
2023.
[80] Dalrymple, D.“davidad”., J. Skalse, Y. Bengio, et al.,
“Towards guaranteed safe AI: A framework for
ensuring robust and reliable AI systems”,
2024.
[81] Linsley, D., P. Zhou, A.K. Ashok, et al., “The
3D-PC: A benchmark for visual
perspective taking in humans and machines”, arXiv
[cs.CV], 2024.
[82] Sinz, F., A.S. Ecker, P. Fahey, et al., “Stimulus
domain transfer in recurrent models for large scale cortical
population prediction on video”, Advances in neural
information processing systems 31, 2018.
[83] Franke, K., K.F. Willeke, K. Ponder, et al.,
“State-dependent pupil dilation rapidly shifts visual
feature selectivity”, Nature 610(7930),
2022, pp. 128–134.
[84] Fu, J., S. Shrinivasan, K. Ponder, et al., “Pattern
completion and disruption characterize contextual modulation in
mouse visual cortex”, bioRxiv and under revision in
Nature, 2023, pp. 2023–03.
[85] Ding, Z., D.T. Tran, K. Ponder, et al., “Bipartite
invariance in mouse primary visual cortex”, bioRxiv and
under revision in Nature, 2023.
[86] Wu, M.C.K., S.V. David, and J.L. Gallant, “Complete
functional characterization of sensory neurons by system
identification”, Annu. Rev. Neurosci. 29,
2006, pp. 477–505.
[87] Lurz, K.-K., M. Bashiri, K. Willeke, et al.,
“Generalization in data-driven models of primary visual
cortex”, (2020).
[88] Cobos, E., T. Muhammad, P.G. Fahey, et al., “It takes
neurons to understand neurons: Digital twins of visual cortex
synthesize neural metamers”, 2022.
[89] Du, F., M.A. Núñez-Ochoa, M. Pachitariu, and C. Stringer,
“Towards a simplified model of primary visual
cortex”, 2024.
[90] Ding, Z., D.T. Tran, K. Ponder, et al., “Bipartite
invariance in mouse primary visual cortex”,
bioRxivorg, 2023.
[91] Cadena, S.A., G.H. Denfield, E.Y. Walker, et al., “Deep
convolutional models improve predictions of macaque
V1 responses to natural images”, PLoS
Comput. Biol. 15(4), 2019, pp. e1006897.
[92] Miao, H.-Y., and F. Tong, “Convolutional neural network
models of neuronal responses in macaque V1 reveal
limited non-linear processing”, bioRxivorg, 2023,
pp. 2023.08.26.554952.
[93] Willeke, K.F., K. Restivo, K. Franke, et al., “Deep
learning-driven characterization of single cell tuning in primate
visual area V4 unveils topological
organization”, bioRxiv, 2023, pp.
2023.05.12.540591.
[94] Cowley, B.R., P.L. Stan, J.W. Pillow, and M.A. Smith,
“Compact deep neural network models of visual
cortex”, 2023.
[95] Cadena, S.A., K.F. Willeke, K. Restivo, et al.,
“Diverse task-driven modeling of macaque V4
reveals functional specialization towards semantic tasks”,
PLoS Comput. Biol. 20(5), 2024, pp. e1012056.
[96] Pierzchlewicz, P.A., K.F. Willeke, A.F. Nix, et al.,
“Energy guided diffusion for generating neurally exciting
images”, 2023.
[97] Wang, T., T.S. Lee, H. Yao, et al., “Large-scale
calcium imaging reveals a systematic V4 map for
encoding natural scenes”, Nat. Commun.
15(1), 2024, pp. 6401.
[98] Rust, N.C., V. Mante, E.P. Simoncelli, and J.A. Movshon,
“How MT cells analyze the motion of visual
patterns”, Nat. Neurosci. 9(11), 2006,
pp. 1421–1431.
[99] Nishimoto, S., and J.L. Gallant, “A three-dimensional
spatiotemporal receptive field model explains responses of area
MT neurons to naturalistic movies”, J.
Neurosci. 31(41), 2011, pp. 14551–14564.
[100] Willmore, B.D.B., R.J. Prenger, and J.L. Gallant,
“Neural representation of natural images in visual area
V2”, Journal of Neuroscience
30(6), 2010, pp. 2102.
[101] Mineault, P.J., F.A. Khawaja, D.A. Butts, and C.C. Pack,
“Hierarchical processing of complex motion along the primate
dorsal visual pathway”, Proc. Natl. Acad. Sci. U. S.
A. 109, 2012, pp. 972–980.
[102] Pasupathy, A., and C.E. Connor, “Population coding of
shape in area V4”, Nat. Neurosci.
5(12), 2002, pp. 1332–1338.
[103] Rançon, U., T. Masquelier, and B.R. Cottereau, “A
general model unifying the adaptive, transient and sustained
properties of ON and OFF auditory neural
responses”, PLoS Comput. Biol. 20(8),
2024, pp. e1012288.
[104] Marin Vargas, A., A. Bisi, A.S. Chiappa, C. Versteeg, L.E.
Miller, and A. Mathis, “Task-driven neural network models
predict neural dynamics of proprioception”, Cell
187(7), 2024, pp. 1745–1761.e19.
[105] Fu, J., S. Shrinivasan, K. Ponder, et al., “Pattern
completion and disruption characterize contextual modulation in
mouse visual cortex”, 2023.
[106] Hubel, D.H., and T.N. Wiesel, “Receptive fields of
single neurones in the cat’s striate cortex”, J.
Physiol. 148, 1959, pp. 574–591.
[107] Olshausen, B.A., and D.J. Field, “What is the other 85
percent of V1 doing?”, In 23 problems in
systems neuroscience. Oxford University PressNew York, 2006,
182–212.
[108] Li, B.M., I.M. Cornacchia, N.L. Rochefort, and A. Onken,
“V1T: Large-scale mouse V1
response prediction using a vision transformer”, arXiv
[cs.CV], 2023.
[109] Kaplan, J., S. McCandlish, T. Henighan, et al.,
“Scaling laws for neural language models”, 2020.
[110] Talebi, V., and C.L. Baker Jr, “Natural versus
synthetic stimuli for estimating receptive field models: A
comparison of predictive robustness”, J. Neurosci.
32(5), 2012, pp. 1560–1576.
[111] Cowley, B., and J.W. Pillow, “High-contrast
“gaudy”images improve the training of deep neural network models
of visual cortex”, Advances in neural information
processing systems, Curran Associates, Inc. (2020),
21591–21603.
[112] Ponce, C.R., W. Xiao, P.F. Schade, T.S. Hartmann, G.
Kreiman, and M.S. Livingstone, “Evolving images for visual
neurons using a deep generative network reveals coding principles
and neuronal preferences”, Cell 177(4),
2019, pp. 999–1009.e10.
[113] Canatar, A., J. Feather, A. Wakhloo, and S. Chung, “A
spectral theory of neural prediction and alignment”,
Neural information processing systems, (2023).
[114] Bashiri, M., E. Walker, K.-K. Lurz, et al., “A
flow-based latent state generative model of neural population
responses to natural images”, Advances in Neural
Information Processing Systems 34, 2021, pp.
15801–15815.
[115] Williams, A.H., E. Kunz, S. Kornblith, and S.W. Linderman,
“Generalized shape metrics on neural
representations”, arXiv:2110.14739 [cs, stat],
2021.
[116] Duong, L.R., J. Zhou, J. Nassar, J. Berman, J. Olieslagers,
and A.H. Williams, “Representational dissimilarity metric
spaces for stochastic neural networks”, 2023.
[117] Kriegeskorte, N., and X.-X. Wei, “Neural tuning and
representational geometry”, Nat. Rev. Neurosci.
22(11), 2021, pp. 703–718.
[118] Yasar, T.B., P. Gombkoto, A.L. Vyssotski, et al.,
“Months-long tracking of neuronal ensembles spanning
multiple brain areas with ultra-flexible tentacle
electrodes”, Nat. Commun. 15(1), 2024,
pp. 4822.
[119] Tootell, R.B.H., D. Tsao, and W. Vanduffel,
“Neuroimaging weighs in: Humans meet macaques in
‘primate’ visual cortex”, J.
Neurosci. 23(10), 2003, pp. 3981–3989.
[120] Liu, X., P. Chen, X. Ding, et al., “A narrative review
of cortical visual prosthesis systems: The latest progress and
significance of nanotechnology for the future”, Ann.
Transl. Med. 10(12), 2022, pp. 716.
[121] St-Yves, G., E.J. Allen, Y. Wu, K. Kay, and T. Naselaris,
“Brain-optimized neural networks learn non-hierarchical
models of representation in human visual cortex”, 2022.
[122] Card, N.S., M. Wairagkar, C. Iacobacci, et al., “An
accurate and rapidly calibrating speech neuroprosthesis”,
2023.
[123] Moses, D.A., S.L. Metzger, J.R. Liu, et al.,
“Neuroprosthesis for decoding speech in a paralyzed person
with anarthria”, N. Engl. J. Med. 385(3),
2021, pp. 217–227.
[124] Bouchard, K.E., N. Mesgarani, K. Johnson, and E.F. Chang,
“Functional organization of human sensorimotor cortex for
speech articulation”, Nature advance online
publication, 2013.
[125] Mathis, M.W., A. Perez Rotondo, E.F. Chang, A.S. Tolias, and
A. Mathis, “Decoding the brain: From neural representations
to mechanistic models”, Cell 187(21),
2024, pp. 5814–5832.
[126] Défossez, A., C. Caucheteux, J. Rapin, O. Kabeli, and J.-R.
King, “Decoding speech from non-invasive brain
recordings”, 2022.
[127] Vaidya, A.R., S. Jain, and A.G. Huth, “Self-supervised
models of audio effectively explain human cortical responses to
speech”, 2022.
[128] Schrimpf, M., I. Blank, G. Tuckute, et al.,
“Artificial neural networks accurately predict language
processing in the brain”, bioRxiv, 2020, pp.
2020.06.26.174482.
[129] Zhou, Z., and C. Firestone, “Humans can decipher
adversarial images”, Nat. Commun. 10(1),
2018, pp. 1334.
[130] Veerabadran, V., J. Goldman, S. Shankar, et al.,
“Subtle adversarial image manipulations influence both human
and machine perception”, Nat. Commun.
14(1), 2023, pp. 4933.
[131] Gaziv, G., M.J. Lee, and J. DiCarlo, “Strong and
precise modulation of human percepts via robustified
ANNs”, Neural Inf Process Syst, 2023.
[132] Dapello, J., K. Kar, M. Schrimpf, et al., “Aligning
model and macaque inferior temporal cortex representations
improves model-to-human behavioral alignment and adversarial
robustness”, 2022.
[133] Li, Z., J. Ortega Caro, E. Rusak, et al., “Robust deep
learning object recognition models rely on low frequency
information in natural images”, PLOS Computational
Biology 19(3), 2023, pp. e1010932.
[134] Pirlot, C., R.C. Gerum, C. Efird, J. Zylberberg, and A.
Fyshe, “Improving the accuracy and robustness of
CNNs using a deep CCA neural data
regularizer”, 2022.
[135] Croce, F., M. Andriushchenko, V. Sehwag, et al.,
“RobustBench: A standardized adversarial
robustness benchmark”, arXiv preprint arXiv:2010.
09670, 2020.
[136] Attias, E., C. Pehlevan, and D. Obeid, “A
brain-inspired regularizer for adversarial robustness”,
arXiv [cs.LG], 2024.
[137] Stevenson, I.H., and K.P. Kording, “How advances in
neural recording affect data analysis”, Nat.
Neurosci. 14(2), 2011, pp. 139–142.
[138] Urai, A.E., B. Doiron, A.M. Leifer, and A.K. Churchland,
“Large-scale neural recordings call for new insights to link
brain and behavior”, Nat Neurosci 25(1),
2022, pp. 11–19.
[139] Manley, J., S. Lu, K. Barber, et al., “Simultaneous,
cortex-wide dynamics of up to 1 million neurons reveal unbounded
scaling of dimensionality with neuron number”,
Neuron 112(10), 2024, pp. 1694–1709.e5.
[140] Richards, B.A., T.P. Lillicrap, P. Beaudoin, et al.,
“A deep learning framework for neuroscience”,
Nat. Neurosci. 22(11), 2019, pp. 1761–1770.
[141] Sandbrink, J., H. Hobbs, J. Swett, A. Dafoe, and A.
Sandberg, “Differential technology development: A
responsible innovation principle for navigating technology
risks”, SSRN Electron. J., 2022.
[142] Hanson, R., The age of em: Work, love, and life when
robots rule the earth, Oxford University Press, London,
England, 2016.
[143] Brunton, S.L., and J.N. Kutz, Data-driven science and
engineering: Machine learning, dynamical systems, and
control, Cambridge University Press, Cambridge, England,
2019.
[144] Zador, A., B. Richards, B. Ölveczky, et al., “Toward
next-generation artificial intelligence: Catalyzing the
NeuroAI revolution”, 2022.
[145] Merel, J., D. Aldarondo, J. Marshall, Y. Tassa, G. Wayne,
and B. Ölveczky, “Deep neuroethology of a virtual
rodent”, arXiv:1911.09451 [q-bio], 2019.
[146] Aldarondo, D., J. Merel, J.D. Marshall, et al., “A
virtual rodent predicts the structure of neural activity across
behaviours”, Nature 632(8025), 2024, pp.
594–602.
[147] Dorkenwald, S., A. Matsliah, A.R. Sterling, et al.,
“Neuronal wiring diagram of an adult brain”,
bioRxiv, 2023, pp. 2023.06.27.546656.
[148] Azevedo, A., E. Lesser, J.S. Phelps, et al.,
“Connectomic reconstruction of a female drosophila ventral
nerve cord”, Nature 631(8020), 2024, pp.
360–368.
[149] Shiu, P.K., G.R. Sterne, N. Spiller, et al., “A
drosophila computational brain model reveals sensorimotor
processing”, Nature 634(8032), 2024, pp.
210–219.
[150] Vaxenburg, R., I. Siwanowicz, J. Merel, et al.,
“Whole-body simulation of realistic fruit fly locomotion
with deep reinforcement learning”, 2024.
[151] Lappalainen, J.K., F.D. Tschopp, S. Prakhya, et al.,
“Connectome-constrained deep mechanistic networks predict
neural responses across the fly visual system at single-neuron
resolution”, 2023.
[152] Cowley, B.R., A.J. Calhoun, N. Rangarajan, et al.,
“Mapping model units to visual neurons reveals population
code for social behaviour”, Nature
629(8014), 2024, pp. 1100–1108.
[153] Cook, S.J., T.A. Jarrell, C.A. Brittin, et al.,
“Whole-animal connectomes of both caenorhabditis elegans
sexes”, Nature 571(7763), 2019, pp.
63–71.
[154] Haspel, G., B. Baker, I. Beets, et al., “The time is
ripe to reverse engineer an entire nervous system: Simulating
behavior from neural interactions”, arXiv
[q-bio.NC], 2023.
[155] Simeon, Q., L.R. Venâncio, K.I. Zhao, et al., “Scaling
properties for artificial neural network models of the \(\textit\{C. elegans\}\) nervous
system”, 2023.
[156] Moravec, H., “Mind children: The future of robot and
human intelligence”, Harvard UP, 1988.
[157] OpenAI, J. Achiam, S. Adler, et al.,
“GPT-4 technical report”, arXiv
[cs.CL], 2023.
[158] Dubey, A., A. Jauhri, A. Pandey, et al., “The llama 3
herd of models”, arXiv [cs.AI], 2024.
[159] Bommasani, R., D.A. Hudson, E. Adeli, et al., “On the
opportunities and risks of foundation models”, 2022.
[160] Paszke, A., S. Gross, F. Massa, et al.,
“PyTorch: An imperative style, high-performance
deep learning library”, 2019.
[161] Wang, R., and Z.S. Chen, “Large-scale foundation
models and generative AI for BigData
neuroscience”, 2023.
[162] Pandarinath, C., D.J. O’Shea, J. Collins, et al.,
“Inferring single-trial neural population dynamics using
sequential auto-encoders”, Nat. Methods
15(10), 2018, pp. 805–815.
[163] Ye, J., and C. Pandarinath, “Representation learning
for neural population activity with neural data
transformers”, 2021.
[164] Hurwitz, C., N. Kudryashova, A. Onken, and M.H. Hennig,
“Building population models for large-scale neural
recordings: Opportunities and pitfalls”, Curr. Opin.
Neurobiol. 70, 2021, pp. 64–73.
[165] Azabou, M., V. Arora, V. Ganesh, et al., “A unified,
scalable framework for neural population decoding”,
Neural information processing systems, (2023).
[166] Zhang, Y., Y. Wang, D. Jimenez-Beneto, et al.,
“Towards a ‘universal translator’ for neural
dynamics at single-cell, single-spike resolution”, 2024.
[167] Schulz, A., J. Vetter, R. Gao, et al., “Modeling
conditional distributions of neural and behavioral data with
masked variational autoencoders”, bioRxiv, 2024,
pp. 2024.04.19.590082.
[168] Caro, J.O., A.H.O. Fonseca, C. Averill, et al.,
“BrainLM: A foundation model for brain activity
recordings”, 2023.
[169] Chau, G., C. Wang, S. Talukder, et al., “Population
transformer: Learning population-level representations of neural
activity”, arXiv [cs.LG], 2024.
[170] Abbaspourazad, S., O. Elachqar, A.C. Miller, S. Emrani, U.
Nallasamy, and I. Shapiro, “Large-scale training of
foundation models for wearable biosignals”, 2024.
[171] Jiang, W., L. Zhao, and B.-L. Lu, “Large brain model
for learning generic representations with tremendous
EEG data in BCI”, (2023).
[172] Csaky, R., M.W.J. van Es, O.P. Jones, and M. Woolrich,
“Foundational GPT model for
MEG”, arXiv [cs.LG], 2024.
[173] Labs, C.-L. at R., D. Sussillo, P. Kaifosh, and T. Reardon,
“A generic noninvasive neuromotor interface for
human-computer interaction”, 2024.
[174] Kupers, E.R., T. Knapen, E.P. Merriam, and K.N. Kay,
“Principles of intensive human neuroimaging”,
Trends Neurosci., 2024.
[175] Yang, C., M. Westover, and J. Sun, “BIOT:
Biosignal transformer for cross-data learning in the wild”,
Neural information processing systems, (2023).
[176] Thomas, A.W., C. Ré, and R.A. Poldrack,
“Self-supervised learning of brain dynamics from broad
neuroimaging data”, 2023.
[177] Thapa, R., B. He, M.R. Kjaer, et al.,
“SleepFM: Foundation model for sleep
analysis”, (2024).
[178] Ho, A., T. Besiroglu, E. Erdil, et al., “Algorithmic
progress in language models”, arXiv [cs.CL], 2024.
[179] Kato, S., H.S. Kaplan, T. Schrödel, et al., “Global
brain dynamics embed the motor command sequence of caenorhabditis
elegans”, Cell 163(3), 2015, pp. 656–669.
[180] Ahrens, M.B., M.B. Orger, D.N. Robson, J.M. Li, and P.J.
Keller, “Whole-brain functional imaging at cellular
resolution using light-sheet microscopy”, Nat.
Methods 10(5), 2013, pp. 413–420.
[181] Gao, P., E. Trautmann, B. Yu, et al., “A theory of
multineuronal dimensionality, dynamics and measurement”,
2017.
[182] Jazayeri, M., and S. Ostojic, “Interpreting neural
computations by examining intrinsic and embedding dimensionality
of neural activity”, arXiv [q-bio.NC], 2021.
[183] Stringer, C., M. Pachitariu, N. Steinmetz, M. Carandini, and
K.D. Harris, “High-dimensional geometry of population
responses in visual cortex”, bioRxiv, 2018, pp.
374090.
[184] Williams, A., “How to cross-validate PCA,
clustering, and matrix decomposition models”, 2018.
[185] Yemini, E., A. Lin, A. Nejatbakhsh, et al.,
“NeuroPAL: A multicolor atlas for whole-brain
neuronal identification in C. elegans”,
Cell 184(1), 2021, pp. 272–288.e11.
[186] Suzuki, R., C. Wen, D. Sprague, S. Onami, and K.D. Kimura,
“Whole-brain spontaneous GCaMP activity with
NeuroPAL cell ID information of
semi-restricted worms”, 2024.
[187] Chen, X., Y. Mu, Y. Hu, et al., “Brain-wide
organization of neuronal activity and convergent sensorimotor
transformations in larval zebrafish”, Neuron
100(4), 2018, pp. 876–890.e5.
[188] Stringer, C., M. Michaelos, D. Tsyboulski, S.E. Lindo, and
M. Pachitariu, “High-precision coding in visual
cortex”, Cell 184(10), 2021, pp.
2767–2778.e15.
[189] Friston, K., “The free-energy principle: A unified
brain theory?”, Nat. Rev. Neurosci.
11(2), 2010, pp. 127–138.
[190] Kluger, D.S., M.G. Allen, and J. Gross, “Brain-body
states embody complex temporal dynamics”, Trends Cogn.
Sci. 28(8), 2024, pp. 695–698.
[191] Zhao, M., N. Wang, X. Jiang, et al.,
“MetaWorm: An integrative data-driven model
simulatingc. Elegansbrain, body and environment
interactions”, bioRxiv, 2024, pp.
2024.02.22.581686.
[192] Lobato-Rios, V., S.T. Ramalingasetty, P.G. Özdil, J.
Arreguit, A.J. Ijspeert, and P. Ramdya,
“NeuroMechFly, a neuromechanical model of adult
drosophila melanogaster”, Nat. Methods
19(5), 2022, pp. 620–627.
[193] Guo, Y., W.J. Veneman, H.P. Spaink, and F.J. Verbeek,
“Three-dimensional reconstruction and measurements of
zebrafish larvae from high-throughput axial-view in vivo
imaging”, Biomed. Opt. Express 8(5),
2017, pp. 2611–2634.
[194] Ramalingasetty, S.T., S.M. Danner, J. Arreguit, et al.,
“A whole-body musculoskeletal model of the mouse”,
IEEE Access 9(99), 2021, pp. 163861–163881.
[195] Gilmer, J.I., S. Coltman, G.C. Velasco, et al., “A
novel biomechanical model of the mouse forelimb predicts muscle
activity in optimal control simulations of reaching
movements”, bioRxivorg, 2024, pp.
2024.09.05.611289.
[196] DeWolf, T., S. Schneider, P. Soubiran, A. Roggenbach, and M.
Mathis, “Neuro-musculoskeletal modeling reveals muscle-level
neural dynamics of adaptive learning in sensorimotor
cortex”, bioRxiv, 2024, pp. 2024.09.11.612513.
[197] Almani, M.N., J. Lazzari, A. Chacon, and S. Saxena,
“μSim: A goal-driven framework for elucidating the neural
control of movement through musculoskeletal modeling”,
bioRxiv, 2024, pp. 2024–02.
[198] Caggiano, V., H. Wang, G. Durandau, M. Sartori, and V.
Kumar, “MyoSuite – a contact-rich simulation
suite for musculoskeletal motor control”, arXiv
[cs.RO], 2022.
[199] Todorov, E., T. Erez, and Y. Tassa,
“MuJoCo: A physics engine for model-based
control”, 2012 IEEE/RSJ international conference on
intelligent robots and systems, IEEE (2012), 5026–5033.
[200] Codol, O., J.A. Michaels, M. Kashefi, J.A. Pruszynski, and
P.L. Gribble, “MotorNet: A python toolbox for
controlling differentiable biomechanical effectors with artificial
neural networks”, eLife, 2024.
[201] Barbagli, F., A. Frisoli, K. Salisbury, and M. Bergamasco,
“Simulating human fingers: A soft finger proxy model and
algorithm”, 12th international symposium on haptic
interfaces for virtual environment and teleoperator systems, 2004.
HAPTICS ’04. proceedings, IEEE (2004), 9–17.
[202] Bhattasali, N.X., A. Zador, and T.A. Engel, “Neural
circuit architectural priors for embodied control”,
Neural Inf Process Syst abs/2201.05242, 2022,
pp. 12744–12759.
[203] Mathis, A., P. Mamidanna, K.M. Cury, et al.,
“DeepLabCut: Markerless pose estimation of
user-defined body parts with deep learning”, Nat.
Neurosci. 21(9), 2018, pp. 1281–1289.
[204] Karashchuk, P., K.L. Rupp, E.S. Dickinson, et al.,
“Anipose: A toolkit for robust markerless 3D
pose estimation”, Cell Rep. 36(13), 2021,
pp. 109730.
[205] Pereira, T.D., N. Tabris, A. Matsliah, et al.,
“SLEAP: A deep learning system for multi-animal
pose tracking”, Nat. Methods 19(4), 2022,
pp. 486–495.
[206] Dunn, T.W., J.D. Marshall, K.S. Severson, et al.,
“Geometric deep learning enables 3D kinematic
profiling across species and environments”, Nat.
Methods 18(5), 2021, pp. 564–573.
[207] Mildenhall, B., P.P. Srinivasan, M. Tancik, J.T. Barron, R.
Ramamoorthi, and R. Ng, “NeRF: Representing
scenes as neural radiance fields for view synthesis”,
arXiv [cs.CV], 2020.
[208] Kerbl, B., G. Kopanas, T. Leimkühler, and G. Drettakis,
“3D gaussian splatting for real-time radiance
field rendering”, arXiv [cs.GR], 2023.
[209] Maheswaranathan, N., L.T. McIntosh, H. Tanaka, et al.,
“Interpreting the retinal neural code for natural scenes:
From computations to neurons”, Neuron
111(17), 2023, pp. 2742–2755.e4.
[210] Seung, H.S., “Predicting visual function by
interpreting a neuronal wiring diagram”, Nature
634(8032), 2024, pp. 113–123.
[211] Bermejo, R., D. Houben, and H.P. Zeigler,
“Optoelectronic monitoring of individual whisker movements
in rats”, J. Neurosci. Methods 83(2),
1998, pp. 89–96.
[212] Knutsen, P.M., D. Derdikman, and E. Ahissar, “Tracking
whisker and head movements in unrestrained behaving
rodents”, J. Neurophysiol. 93(4), 2005,
pp. 2294–2301.
[213] Wilson, A.D., and M. Baietto, “Applications and
advances in electronic-nose technologies”, Sensors
(Basel) 9(7), 2009, pp. 5099–5148.
[214] Mamiya, A., P. Gurung, and J.C. Tuthill, “Neural
coding of leg proprioception in drosophila”,
Neuron 100(3), 2018, pp. 636–650.e6.
[215] Mamiya, A., A. Sustar, I. Siwanowicz, et al.,
“Biomechanical origins of proprioceptor feature selectivity
and topographic maps in the drosophila leg”,
Neuron 111(20), 2023, pp. 3230–3243.e14.
[216] Martinelli, F., B. Simsek, W. Gerstner, and J. Brea,
“Expand-and-cluster: Parameter recovery of neural
networks”, 2024.
[217] Liu, H.X., and S. Feng, “Curse of rarity for
autonomous vehicles”, Nat. Commun. 15(1),
2024, pp. 4808.
[218] Beiran, M., and A. Litwin-Kumar, “Prediction of neural
activity in connectome-constrained recurrent networks”,
2024.
[219] Pearl, J., Causality: Models, reasoning, and
inference, Cambridge University Press, Cambridge, England,
2009.
[220] Bailey, D.H., A.J. Jung, A.M. Beltz, et al., “Causal
inference on human behaviour”, Nature Human
Behavior 8(8), 2024, pp. 1448–1459.
[221] Zhao, W., J.P. Queralta, and T. Westerlund,
“Sim-to-real transfer in deep reinforcement learning for
robotics: A survey”, arXiv [cs.LG], 2020.
[222] Howard, J., and S. Ruder, “Universal language model
fine-tuning for text classification”, arXiv
[cs.CL], 2018.
[223] O’Byrne, J., and K. Jerbi, “How critical is brain
criticality?”, Trends Neurosci. 45(11),
2022, pp. 820–837.
[224] Rust, N., “Is the brain uncontrollable, like the
weather?”, 2023.
[225] Bischoff, S., A. Darcher, M. Deistler, et al., “A
practical guide to statistical distances for evaluating generative
models in science”, arXiv [cs.LG], 2024.
[226] Ostrow, M., A. Eisen, L. Kozachkov, and I. Fiete,
“Beyond geometry: Comparing the temporal structure of
computation in neural circuits with dynamical similarity
analysis”, Advances in Neural Information Processing
Systems 36, 2024.
[227] Heusel, M., H. Ramsauer, T. Unterthiner, B. Nessler, and S.
Hochreiter, “GANs trained by a two time-scale
update rule converge to a local nash equilibrium”,
Advances in Neural Information Processing Systems
30, 2017.
[228] Zheng, L., W.-L. Chiang, Y. Sheng, et al., “Judging
LLM-as-a-judge with MT-bench and chatbot
arena”, arXiv [cs.CL], 2023.
[229] Sarma, G.P., A. Safron, and N.J. Hay, “Integrative
biological simulation, neuropsychology, and AI
safety”, 2019.
[230] Einevoll, G.T., A. Destexhe, M. Diesmann, et al., “The
scientific case for brain simulations”, arXiv
[q-bio.NC], 2019.
[231] Haufler, D., S. Ito, C. Koch, and A. Arkhipov,
“Simulations of cortical networks using spatially extended
conductance-based neuronal models”, J. Physiol.
601(15), 2023, pp. 3123–3139.
[232] Wellcome Trust, “Scaling up connectomics: The road to
a whole mouse brain connectome”, 2023.
[233] Pospisil, D.A., M.J. Aragon, S. Dorkenwald, et al.,
“The fly connectome reveals a path to the effectome”,
Nature 634(8032), 2024, pp. 201–209.
[234] Lu, W., L. Zeng, X. Du, et al., “Digital twin brain: A
simulation and assimilation platform for whole human
brain”, arXiv [cs.NE], 2023.
[235] Yamaura, H., J. Igarashi, and T. Yamazaki, “Simulation
of a human-scale cerebellar network model on the K
computer”, Front. Neuroinform. 14, 2020,
pp. 16.
[236] Marblestone*, A.H., B.M. Zamft*, Y.G. Maguire, et al.,
“Physical principles for scalable neural recording”,
Front. Comput. Neurosci. 7, 2013.
[237] Januszewski, M., and V. Jain, “Next-generation
AI for connectomics”, Nat. Methods
21(8), 2024, pp. 1398–1399.
[238] Haehn, D., J. Hoffer, B. Matejek, et al., “Scalable
interactive visualization for connectomics”,
Informatics (MDPI) 4(3), 2017, pp. 29.
[239] White, J.G., E. Southgate, J.N. Thomson, and S. Brenner,
“The structure of the nervous system of the nematode
caenorhabditis elegans”, Philos. Trans. R. Soc. Lond. B
Biol. Sci. 314(1165), 1986, pp. 1–340.
[240] Consortium, T.M., J.A. Bae, M. Baptiste, et al.,
“Functional connectomics spanning multiple areas of mouse
visual cortex”, 2023.
[241] Winding, M., B.D. Pedigo, C.L. Barnes, et al., “The
connectome of an insect brain”, Science
379(6636), 2023, pp. eadd9330.
[242] Shapson-Coe, A., M. Januszewski, D.R. Berger, et al.,
“A petavoxel fragment of human cerebral cortex reconstructed
at nanoscale resolution”, Science
384(6696), 2024, pp. eadk4858.
[243] Zheng, Z., C.S. Own, A.A. Wanner, et al., “Fast
imaging of millimeter-scale areas with beam deflection
transmission electron microscopy”, Nat. Commun.
15(1), 2024, pp. 6860.
[244] Januszewski, M., J. Kornfeld, P.H. Li, et al.,
“High-precision automated reconstruction of neurons with
flood-filling networks”, Nat. Methods
15(8), 2018, pp. 605–610.
[245] Sheridan, A., T.M. Nguyen, D. Deb, et al., “Local
shape descriptors for neuron segmentation”, Nat.
Methods 20(2), 2023, pp. 295–303.
[246] Kebschull, J.M., and A.M. Zador, “Cellular barcoding:
Lineage tracing, screening and beyond”, Nat.
Methods 15(11), 2018, pp. 871–879.
[247] Chen, X., Y.-C. Sun, H. Zhan, et al., “High-throughput
mapping of long-range neuronal projection using in situ
sequencing”, Cell 179(3), 2019, pp.
772–786.e19.
[248] Livet, J., T.A. Weissman, H. Kang, et al., “Transgenic
strategies for combinatorial expression of fluorescent proteins in
the nervous system”, Nature 450(7166),
2007, pp. 56–62.
[249] Viswanathan, S., M.E. Williams, E.B. Bloss, et al.,
“High-performance probes for light and electron
microscopy”, Nat. Methods 12(6), 2015,
pp. 568–576.
[250] Mishchenko, Y., “On optical detection of densely
labeled synapses in neuropil and mapping connectivity with
combinatorially multiplexed fluorescent synaptic markers”,
PLoS One 5(1), 2010, pp. e8853.
[251] Marblestone, A.H., and E.S. Boyden, “Designing tools
for assumption-proof brain mapping”, Neuron
83(6), 2014, pp. 1239–1241.
[252] Qihua, C., C. Xuejin, W. Chenxuan, L. Yixiong, X. Zhiwei,
and W. Feng, “Learning multimodal volumetric features for
large-scale neuron tracing”, arXiv [cs.CV], 2024.
[253] Chen, F., P.W. Tillberg, and E.S. Boyden, “Optical
imaging. Expansion microscopy”, Science
347(6221), 2015, pp. 543–548.
[254] Tavakoli, M.R., J. Lyudchik, M. Januszewski, et al.,
“Light-microscopy based dense connectomic reconstruction of
mammalian brain tissue”, bioRxiv, 2024, pp.
2024.03.01.582884.
[255] Alon, S., D.R. Goodwin, A. Sinha, et al., “Expansion
sequencing: Spatially precise in situ transcriptomics in intact
biological systems”, Science 371(6528),
2021, pp. eaax2656.
[256] Kang, J., M.E. Schroeder, Y. Lee, et al., “Multiplexed
expansion revealing for imaging multiprotein nanostructures in
healthy and diseased brain”, Nat. Commun.
15(1), 2024, pp. 9722.
[257] Adamhmarblestone, P. by, “On whole-mammalian-brain
connectomics”, 2019.
[258] Rodriques, S., “Optical microscopy provides a path to
a $10M mouse brain connectome (if it eliminates
proofreading)”, 2023. https://www.sam-rodriques.com/post/optical-microscopy-provides-a-path-to-a-10m-mouse-brain-connectome-if-it-eliminates-proofreading
[259] Linghu, C., S.L. Johnson, P.A. Valdes, et al.,
“Spatial multiplexing of fluorescent reporters for imaging
signaling network dynamics”, Cell 183(6),
2020, pp. 1682–1698.e24.
[260] Zador, A.M., J. Dubnau, H.K. Oyibo, H. Zhan, G. Cao, and
I.D. Peikon, “Sequencing the connectome”, PLoS
Biol. 10(10), 2012, pp. e1001411.
[261] Shin, D., M.E. Urbanek, H.H. Larson, et al.,
“High-complexity barcoded rabies virus for scalable circuit
mapping using single-cell and single-nucleus sequencing”,
bioRxiv, 2024, pp. 2024–10.
[262] Arkhipov, A., N.W. Gouwens, Y.N. Billeh, et al.,
“Visual physiology of the layer 4 cortical circuit in
silico”, PLoS Comput. Biol. 14(11), 2018,
pp. e1006535.
[263] Holler, S., G. Köstinger, K.A.C. Martin, G.F.P. Schuhknecht,
and K.J. Stratford, “Structure and function of a neocortical
synapse”, Nature 591(7848), 2021, pp.
111–116.
[264] Campagnola, L., S.C. Seeman, T. Chartrand, et al.,
“Local connectivity and synaptic dynamics in mouse and human
neocortex”, Science 375(6585), 2022, pp.
eabj5861.
[265] Sanfilippo, P., A.J. Kim, A. Bhukel, et al., “Mapping
of multiple neurotransmitter receptor subtypes and distinct
protein complexes to the connectome”, Neuron
112(6), 2024, pp. 942–958.e13.
[266] Lee, H.S., A. Ghetti, A. Pinto-Duarte, et al.,
“Astrocytes contribute to gamma oscillations and recognition
memory”, Proc. Natl. Acad. Sci. U. S. A.
111(32), 2014, pp. E3343–52.
[267] Shen, F.Y., M.M. Harrington, L.A. Walker, H.P.J. Cheng, E.S.
Boyden, and D. Cai, “Light microscopy based approach for
mapping connectivity with molecular specificity”, Nat.
Commun. 11(1), 2020, pp. 4632.
[268] Cadwell, C.R., A. Palasantza, X. Jiang, et al.,
“Electrophysiological, transcriptomic and morphologic
profiling of single neurons using patch-seq”, Nature
biotechnology 34(2), 2016, pp. 199–203.
[269] Fuzik, J., A. Zeisel, Z. Máté, et al., “Integration of
electrophysiological recordings with single-cell RNA-seq data
identifies neuronal subtypes”, Nature
biotechnology 34(2), 2016, pp. 175–183.
[270] Scala, F., D. Kobak, M. Bernabucci, et al.,
“Phenotypic variation of transcriptomic cell types in mouse
motor cortex”, Nature 598(7879), 2021,
pp. 144–150.
[271] Lee, B.R., A. Budzillo, K. Hadley, et al., “Scaled,
high fidelity electrophysiological, morphological, and
transcriptomic cell characterization”, Elife
10, 2021.
[272] Gouwens, N.W., S.A. Sorensen, F. Baftizadeh, et al.,
“Integrated morphoelectric and transcriptomic classification
of cortical GABAergic cells”, Cell
183(4), 2020, pp. 935–953.e19.
[273] Berg, J., S.A. Sorensen, J.T. Ting, et al., “Human
neocortical expansion involves glutamatergic neuron
diversification”, Nature 598(7879), 2021,
pp. 151–158.
[274] Atanas, A.A., J. Kim, Z. Wang, et al., “Brain-wide
representations of behavior spanning multiple timescales and
states in C. elegans”, Cell
186(19), 2023, pp. 4134–4151.e31.
[275] Vries, S.E.J. de, J.A. Lecoq, M.A. Buice, et al., “A
large-scale standardized physiological survey reveals functional
organization of the mouse visual cortex”, Nat.
Neurosci. 23(1), 2020, pp. 138–151.
[276] Siegle, J.H., X. Jia, S. Durand, et al., “Survey of
spiking in the mouse visual system reveals functional
hierarchy”, Nature 592(7852), 2021, pp.
86–92.
[277] Leonard, M.K., L. Gwilliams, K.K. Sellers, et al.,
“Large-scale single-neuron speech sound encoding across the
depth of human cortex”, Nature 626(7999),
2024, pp. 593–602.
[278] Khanna, A.R., W. Muñoz, Y.J. Kim, et al.,
“Single-neuronal elements of speech production in
humans”, Nature 626(7999), 2024, pp.
603–610.
[279] Creamer, M.S., A.M. Leifer, and J.W. Pillow, “Bridging
the gap between the connectome and whole-brain activity inc.
Elegans”, bioRxiv, 2024.
[280] Shen, F.X., M.L. Baum, N. Martinez-Martin, et al.,
“Returning individual research results from digital
phenotyping in psychiatry”, Am. J. Bioeth.
24(2), 2024, pp. 69–90.
[281] Bugeon, S., J. Duffield, M. Dipoppa, et al., “A
transcriptomic axis predicts state modulation of cortical
interneurons”, Nature 607(7918), 2022,
pp. 330–338.
[282] Condylis, C., A. Ghanbari, N. Manjrekar, et al.,
“Dense functional and molecular readout of a circuit hub in
sensory cortex”, Science 375(6576), 2022,
pp. eabl5981.
[283] M’Saad, O., and J. Bewersdorf, “Light microscopy of
proteins in their ultrastructural context”, Nat.
Commun. 11(1), 2020, pp. 3850.
[284] Zinchenko, V., J. Hugger, V. Uhlmann, D. Arendt, and A.
Kreshuk, “MorphoFeatures for unsupervised
exploration of cell types, tissues, and organs in volume electron
microscopy”, Elife 12, 2023.
[285] Gamlin, C.R., C.M. Schneider-Mizell, M. Mallory, et al.,
“Integrating EM and patch-seq data: Synaptic
connectivity and target specificity of predicted sst
transcriptomic types”, bioRxivorg, 2023.
[286] Randi, F., A.K. Sharma, S. Dvali, and A.M. Leifer,
“Neural signal propagation atlas of caenorhabditis
elegans”, Nature, 2023, pp. 1–9.
[287] Gouwens, N.W., J. Berg, D. Feng, et al., “Systematic
generation of biophysically detailed models for diverse cortical
neuron types”, Nat. Commun. 9(1), 2018,
pp. 710.
[288] Billeh, Y.N., B. Cai, S.L. Gratiy, et al., “Systematic
integration of structural and functional data into multi-scale
models of mouse primary visual cortex”, Neuron
106(3), 2020, pp. 388–403.e18.
[289] Markram, H., E. Muller, S. Ramaswamy, et al.,
“Reconstruction and simulation of neocortical
microcircuitry”, Cell 163(2), 2015, pp.
456–492.
[290] Zhang, Y., G. He, L. Ma, et al., “A
GPU-based computational framework that bridges neuron
simulation and artificial intelligence”, Nat.
Commun. 14(1), 2023, pp. 5798.
[291] Dura-Bernal, S., S.A. Neymotin, B.A. Suter, et al.,
“Multiscale model of primary motor cortex circuits predicts
in vivo cell-type-specific, behavioral state-dependent
dynamics”, Cell Rep. 42(6), 2023, pp.
112574.
[292] Hagen, E., D. Dahmen, M.L. Stavrinou, et al., “Hybrid
scheme for modeling local field potentials from point-neuron
networks”, Cereb. Cortex 26(12), 2016,
pp. 4461–4496.
[293] Rimehaug, A.E., A.J. Stasik, E. Hagen, et al.,
“Uncovering circuit mechanisms of current sinks and sources
with biophysical simulations of primary visual cortex”,
Elife 12, 2023.
[294] Stevens, R., and G. Orr, Bioimaging capabilities to
enable mapping of the neural connections in a complex
brain, US Department of Energy (USDOE), Washington DC
(United States), 2020.
[295] Simeon, Q., A. Kashyap, K.P. Kording, and E.S. Boyden,
“Homogenized \(\textit{C.
elegans}\) neural activity and connectivity data”,
2024. https://arxiv.org/abs/2411.12091
[296] Wong, L., G. Grand, A.K. Lew, et al., “From word
models to world models: Translating from natural language to the
probabilistic language of thought”, arXiv preprint
arXiv:2306.12672, 2023.
[297] Sumers, T.R., S. Yao, K. Narasimhan, and T.L. Griffiths,
“Cognitive architectures for language agents”,
arXiv preprint arXiv:2309.02427, 2023.
[298] Binz, M., I. Dasgupta, A.K. Jagadish, M. Botvinick, J.X.
Wang, and E. Schulz, “Meta-learned models of
cognition”, Behavioral and Brain Sciences
47, 2024, pp. e147.
[299] Lieder, F., and T.L. Griffiths, “Resource-rational
analysis: Understanding human cognition as the optimal use of
limited computational resources”, Behavioral and brain
sciences 43, 2020, pp. e1.
[300] Gershman, S.J., E.J. Horvitz, and J.B. Tenenbaum,
“Computational rationality: A converging paradigm for
intelligence in brains, minds, and machines”,
Science 349(6245), 2015, pp. 273–278.
[301] Icard, T., “Resource rationality”, Book
manuscript, 2023.
[302] Newell, A., Unified theories of cognition, Harvard
University Press, 1994.
[303] Spelke, E.S., What babies know: Core knowledge and
composition volume 1, Oxford University Press, 2022.
[304] Chollet, F., M. Knoop, B. Landers, et al., “ARC prize
2024”, 2024.
[305] Ellis, K., C. Wong, M. Nye, et al.,
DreamCoder: Growing generalizable, interpretable
knowledge with wake-sleep bayesian program learning, arXiv,
2020.
[306] Chollet, F., “On the measure of intelligence”,
2019.
[307] Moskvichev, A., V.V. Odouard, and M. Mitchell, “The
conceptarc benchmark: Evaluating understanding and generalization
in the arc domain”, arXiv preprint
arXiv:2305.07141, 2023.
[308] Wüst, A., T. Tobiasch, L. Helff, D.S. Dhami, C.A. Rothkopf,
and K. Kersting, “Bongard in wonderland: Visual puzzles that
still make AI go mad?”, arXiv preprint
arXiv:2410.19546, 2024.
[309] Bakhtin, A., L. van der Maaten, J. Johnson, L. Gustafson,
and R. Girshick, “Phyre: A new benchmark for physical
reasoning”, Advances in Neural Information Processing
Systems 32, 2019.
[310] Bear, D.M., E. Wang, D. Mrowca, et al., “Physion:
Evaluating physical prediction from vision in humans and
machines”, arXiv preprint arXiv:2106.08261, 2021.
[311] Kirfel, L., T. Icard, and T. Gerstenberg, “Inference
from explanation.”, Journal of Experimental Psychology:
General 151(7), 2022, pp. 1481.
[312] Sun, J.J., A. Ulmer, D. Chakraborty, et al., “The
MABe22 benchmarks for representation learning of multi-agent
behavior”, arXiv preprint arXiv:2207.10553, 2022.
[313] Smith, M.L., J.D. Davidson, B. Wild, D.M. Dormagen, T.
Landgraf, and I.D. Couzin, “Behavioral variation across the
days and lives of honey bees”, Iscience
25(9), 2022.
[314] Matzner, S., T. Warfel, and R. Hull,
“ThermalTracker-3D: A thermal stereo vision system for
quantifying bird and bat activity at offshore wind energy
sites”, Ecological Informatics 57, 2020,
pp. 101069.
[315] Van Horn, G., S. Branson, R. Farrell, et al.,
“Building a bird recognition app and large scale dataset
with citizen scientists: The fine print in fine-grained dataset
collection”, Proceedings of the IEEE conference on
computer vision and pattern recognition, (2015), 595–604.
[316] Koger, B., A. Deshpande, J.T. Kerby, J.M. Graving, B.R.
Costelloe, and I.D. Couzin, “Quantifying the movement,
behaviour and environmental context of group-living animals using
drones and computer vision”, Journal of Animal
Ecology, 2023.
[317] Naik, H., A.H.H. Chan, J. Yang, et al., “3D-POP–an
automated annotation approach to facilitate markerless 2D-3D
tracking of freely moving birds with marker-based motion
capture”, arXiv preprint arXiv:2303.13174, 2023.
[318] Allen, K., F. Brändle, M. Botvinick, et al., “Using
games to understand the mind”, Nature Human
Behaviour, 2024, pp. 1–9.
[319] Mnih, V., N. Heess, A. Graves, and K. Kavukcuoglu,
“Recurrent models of visual attention”, 2014.
[320] Badia, A.P., B. Piot, S. Kapturowski, et al.,
“Agent57: Outperforming the atari human benchmark”,
International conference on machine learning, PMLR
(2020), 507–517.
[321] Xue, C., V. Pinto, C. Gamage, E. Nikonova, P. Zhang, and J.
Renz, “Phy-q as a measure for physical reasoning
intelligence”, Nature Machine Intelligence
5(1), 2023, pp. 83–93.
[322] Das, R., J.B. Tenenbaum, A. Solar-Lezama, and Z. Tavares,
“Combining functional and automata synthesis to discover
causal reactive programs”, Proceedings of the ACM on
Programming Languages 7(POPL), 2023, pp. 1628–1658.
[323] Chowdhary, S., I. Iacopini, and F. Battiston,
“Quantifying human performance in chess”,
Scientific Reports 13(1), 2023, pp. 2113.
[324] Meta Fundamental AI Research Diplomacy Team (FAIR)†, A.
Bakhtin, N. Brown, et al., “Human-level play in the game of
diplomacy by combining language models with strategic
reasoning”, Science 378(6624), 2022, pp.
1067–1074.
[325] Russek, E., D. Acosta-Kane, B. van Opheusden, M.G. Mattar,
and T. Griffiths, “Time spent thinking in online chess
reflects the value of computation”, PsyArXiv,
2022.
[326] Gao, P., and S. Ganguli, “On simplicity and complexity
in the brave new world of large-scale neuroscience”,
Curr. Opin. Neurobiol. 32, 2015, pp. 148–155.
[327] Krakauer, J.W., A.A. Ghazanfar, A. Gomez-Marin, M.A.
MacIver, and D. Poeppel, “Neuroscience needs behavior:
Correcting a reductionist bias”, Neuron
93(3), 2017, pp. 480–490.
[328] Mobbs, D., P.C. Trimmer, D.T. Blumstein, and P. Dayan,
“Foraging for foundations in decision neuroscience: Insights
from ethology”, Nat. Rev. Neurosci.
19(7), 2018, pp. 419–427.
[329] Hall-McMaster, S., and F. Luyckx, “Revisiting foraging
approaches in neuroscience”, Cogn. Affect. Behav.
Neurosci. 19(2), 2019, pp. 225–230.
[330] Pinto, L., K. Rajan, B. DePasquale, S.Y. Thiberge, D.W.
Tank, and C.D. Brody, “Task-dependent changes in the
large-scale dynamics and necessity of cortical regions”,
Neuron 104(4), 2019, pp. 810–824.e9.
[331] Miller, C.T., D. Gire, K. Hoke, et al., “Natural
behavior is the language of the brain”, Curr.
Biol. 32(10), 2022, pp. R482–R493.
[332] Dennis, E.J., A. El Hady, A. Michaiel, et al.,
“Systems neuroscience of natural behaviors in
rodents”, J. Neurosci. 41(5), 2021, pp.
911–919.
[333] Niv, Y., “The primacy of behavioral research for
understanding the brain”, Behav. Neurosci.
135(5), 2021, pp. 601–609.
[334] Driscoll, L.N., K. Shenoy, and D. Sussillo, “Flexible
multitask computation in recurrent networks utilizes shared
dynamical motifs”, Nat. Neurosci. 27(7),
2024, pp. 1349–1363.
[335] Peterson, J.C., D.D. Bourgin, M. Agrawal, D. Reichman, and
T.L. Griffiths, “Using large-scale experiments and machine
learning to discover theories of human decision-making”,
Science 372(6547), 2021, pp. 1209–1214.
[336] Binz, M., E. Akata, M. Bethge, et al., “Centaur: A
foundation model of human cognition”, arXiv preprint
arXiv:2410.20268, 2024.
[337] Strauch, C., C.-A. Wang, W. Einhäuser, S. Van der Stigchel,
and M. Naber, “Pupillometry as an integrated readout of
distinct attentional networks”, Trends in
Neurosciences 45(8), 2022, pp. 635–647.
[338] Sirois, S., and J. Brisson, “Pupillometry”,
Wiley Interdisciplinary Reviews: Cognitive Science
5(6), 2014, pp. 679–692.
[339] Fan, Z., Y. Zhu, Y. He, Q. Sun, H. Liu, and J. He,
“Deep learning on monocular object pose detection and
tracking: A comprehensive overview”, ACM Computing
Surveys 55(4), 2022, pp. 1–40.
[340] Kendall, A., M. Grimes, and R. Cipolla, “Posenet: A
convolutional network for real-time 6-dof camera
relocalization”, Proceedings of the IEEE international
conference on computer vision, (2015), 2938–2946.
[341] Freer, C.E., D.M. Roy, and J.B. Tenenbaum, “Towards
common-sense reasoning via conditional simulation: Legacies of
turing in artificial intelligence.”, Turing’s
Legacy 42, 2014, pp. 195–252.
[342] Goodman, N., V. Mansinghka, D.M. Roy, K. Bonawitz, and J.B.
Tenenbaum, “Church: A language for generative
models”, arXiv preprint arXiv:1206.3255, 2012.
[343] Carpenter, B., A. Gelman, M.D. Hoffman, et al., “Stan:
A probabilistic programming language”, Journal of
statistical software 76, 2017.
[344] Goodman, N.D., and A. Stuhlmüller, “The Design and Implementation of Probabilistic
Programming Languages”, 2014.
[345] Abril-Pla, O., V. Andreani, C. Carroll, et al., “PyMC:
A modern, and comprehensive probabilistic programming framework in
python”, PeerJ Computer Science 9, 2023,
pp. e1516.
[346] Bingham, E., J.P. Chen, M. Jankowiak, et al., “Pyro:
Deep universal probabilistic programming”, Journal of
machine learning research 20(28), 2019, pp. 1–6.
[347] Phan, D., N. Pradhan, and M. Jankowiak, “Composable
effects for flexible and accelerated probabilistic programming in
NumPyro”, arXiv preprint arXiv:1912.11554, 2019.
[348] Ge, H., K. Xu, and Z. Ghahramani, “Turing: A language
for flexible probabilistic inference”, International
conference on artificial intelligence and statistics, PMLR
(2018), 1682–1690.
[349] Cusumano-Towner, M.F., F.A. Saad, A.K. Lew, and V.K.
Mansinghka, “Gen: A general-purpose probabilistic
programming system with programmable inference”,
Proceedings of the 40th acm sigplan conference on programming
language design and implementation, (2019), 221–236.
[350] Meent, J.-W. van de, B. Paige, H. Yang, and F. Wood,
“An introduction to probabilistic programming”,
arXiv preprint arXiv:1809.10756, 2018.
[351] Chaudhuri, S., K. Ellis, O. Polozov, et al.,
“Neurosymbolic programming”, Foundations and
Trends in Programming Languages 7(3),
2021, pp. 158–243.
[352] Botvinick, M., and M. Toussaint, “Planning as
inference”, Trends in cognitive sciences
16(10), 2012, pp. 485–488.
[353] Milli, S., F. Lieder, and T.L. Griffiths, “A rational
reinterpretation of dual-process theories”,
Cognition 217, 2021, pp. 104881.
[354] Pearl, J., “The algorithmization of
counterfactuals”, Annals of Mathematics and Artificial
Intelligence 61, 2011, pp. 29–39.
[355] Solway, A., and M.M. Botvinick, “Goal-directed
decision making as probabilistic inference: A computational
framework and potential neural correlates.”,
Psychological review 119(1), 2012, pp. 120.
[356] Koller, D., “Probabilistic graphical models:
Principles and techniques”, 2009.
[357] Tavares, Z., J. Koppel, X. Zhang, R. Das, and A.
Solar-Lezama, “A language for counterfactual generative
models”, International conference on machine
learning, PMLR (2021), 10173–10182.
[358] Dawid, A.P., “Influence diagrams for causal modelling
and inference”, International Statistical Review
70(2), 2002, pp. 161–189.
[359] MacDermott, M., T. Everitt, and F. Belardinelli,
“Characterising decision theories with mechanised causal
graphs”, 2023. https://arxiv.org/abs/2307.10987
[360] Hammond, L., J. Fox, T. Everitt, R. Carey, A. Abate, and M.
Wooldridge, “Reasoning about
causality in games (abstract reprint)”, Proceedings
of the AAAI Conference on Artificial Intelligence
38(20), 2024, pp. 22697–22697.
[361] Levine, S., “Reinforcement learning and control as
probabilistic inference: Tutorial and review”, arXiv
[cs.LG], 2018.
[362] Everitt, T., R. Kumar, V. Krakovna, and S. Legg,
“Modeling AGI safety frameworks with causal influence
diagrams”, 2019. https://arxiv.org/abs/1906.08663
[363] Kenton, Z., R. Kumar, S. Farquhar, J. Richens, M.
MacDermott, and T. Everitt, “Discovering
agents”, Artificial Intelligence 322,
2023, pp. 103963.
[364] Richens, J., and T. Everitt, “Robust agents learn
causal world models”, 2024. https://arxiv.org/abs/2402.10877
[365] Everitt, T., M. Hutter, R. Kumar, and V. Krakovna,
“Reward tampering problems and solutions in reinforcement
learning: A causal influence diagram perspective”,
Synthese 198(Suppl 27), 2021, pp. 6435–6467.
[366] Tavares, Z., X. Zhang, E. Minaysan, J. Burroni, R.
Ranganath, and A.S. Lezama, “The random conditional
distribution for higher-order probabilistic inference”,
arXiv preprint arXiv:1903.10556, 2019.
[367] Stuhlmüller, A., and N.D. Goodman, “Reasoning about
reasoning by nested conditioning: Modeling theory of mind with
probabilistic programs”, Cognitive Systems
Research 28, 2014, pp. 80–99.
[368] Evans, O., A. Stuhlmüller, J. Salvatier, and D. Filan,
“Modeling Agents with Probabilistic
Programs”, 2017.
[369] Goodman, N.D., J.B. Tenenbaum, and T.P. Contributors,
“Probabilistic Models of
Cognition”, 2016.
[370] Belle, V., and L. De Raedt, “Semiring programming: A
framework for search, inference and learning”, CoRR,
abs/1609.06954, 2016.
[371] Hinton, G.E., P. Dayan, B.J. Frey, and R.M. Neal,
“The" wake-sleep" algorithm for unsupervised neural
networks”, Science 268(5214), 1995, pp.
1158–1161.
[372] Stuhlmüller, A., J. Taylor, and N. Goodman, “Learning
stochastic inverses”, Advances in neural information
processing systems 26, 2013.
[373] Piantadosi, S.T., and R.A. Jacobs, “Four problems
solved by the probabilistic language of thought”,
Current Directions in Psychological Science
25(1), 2016, pp. 54–59.
[374] Neal, R.M., “New monte carlo methods based on
hamiltonian dynamics”, MaxEnt workshop, number
july, (2011).
[375] Delaloye, S., and P.E. Holtzheimer, “Deep brain
stimulation in the treatment of depression”, Dialogues
Clin. Neurosci. 16(1), 2014, pp. 83–91.
[376] Holtzheimer, P.E., and H.S. Mayberg, “Deep brain
stimulation for psychiatric disorders”, Annu. Rev.
Neurosci. 34(1), 2011, pp. 289–307.
[377] Oxley, T.J., N.L. Opie, S.E. John, et al., “Minimally
invasive endovascular stent-electrode array for high-fidelity,
chronic recordings of cortical neural activity”, Nat.
Biotechnol. 34(3), 2016, pp. 320–327.
[378] Musk, E., and Neuralink, “An integrated brain-machine
interface platform with thousands of channels”,
bioRxiv, 2019, pp. 703801.
[379] Sahasrabuddhe, K., A.A. Khan, A.P. Singh, et al., “The
argo: A 65,536 channel recording system for high density neural
recordingin vivo”, bioRxiv, 2020, pp.
2020.07.17.209403.
[380] Paulk, A.C., Y. Kfir, A.R. Khanna, et al.,
“Large-scale neural recordings with single neuron resolution
using neuropixels probes in human cortex”, Nat.
Neurosci. 25(2), 2022, pp. 252–263.
[381] Nishimoto, S., A.T. Vu, T. Naselaris, Y. Benjamini, B. Yu,
and J.L. Gallant, “Reconstructing visual experiences from
brain activity evoked by natural movies”, Curr.
Biol. 21(19), 2011, pp. 1641–1646.
[382] Scotti, P., A. Banerjee, J. Goode, et al.,
“Reconstructing the mind’s eye: fMRI-to-image with contrastive learning and
diffusion priors”, Neural information processing
systems, (2023).
[383] Christiano, P.F., J. Leike, T. Brown, M. Martic, S. Legg,
and D. Amodei, “Deep reinforcement learning from human
preferences”, Advances in neural information processing
systems 30, 2017.
[384] Fong, R.C., W.J. Scheirer, and D.D. Cox, “Using human
brain activity to guide machine learning”, Sci.
Rep. 8(1), 2018, pp. 5397.
[385] Nisbett, R.E., and T.D. Wilson, “Telling more than we
can know: Verbal reports on mental processes”, Psychol.
Rev. 84(3), 1977, pp. 231.
[386] Lightman, H., V. Kosaraju, Y. Burda, et al., “Let’s
verify step by step”, arXiv [cs.LG], 2023.
[387] Luo, L., Y. Liu, R. Liu, et al., “Improve mathematical
reasoning in language models by automated process
supervision”, arXiv [cs.CL], 2024.
[388] Hendrycks, D., C. Burns, S. Basart, et al., “Aligning
AI with shared human values”, arXiv
[cs.CY], 2020.
[389] Sharma, M., M. Tong, T. Korbak, et al., “Towards
understanding sycophancy in language models”, arXiv
[cs.CL], 2023.
[390] Shen, T., R. Jin, Y. Huang, et al., “Large language
model alignment: A survey”, arXiv [cs.CL], 2023.
[391] Phuong, M., M. Aitchison, E. Catt, et al., “Evaluating
frontier models for dangerous capabilities”, arXiv
[cs.LG], 2024.
[392] Müller, V.C., “Ethics of artificial intelligence and
robotics”, 2020.
[393] OpenAI, “Introducing OpenAI o1”, 2024.
[394] Abdin, M., J. Aneja, H. Awadalla, et al., “Phi-3
technical report: A highly capable language model locally on your
phone”, arXiv [cs.CL], 2024.
[395] Branwen, G., “WBE and DRL: A
middle way of imitation learning from the human brain”,
2018.
[396] Sucholutsky, I., and T.L. Griffiths, “Alignment with
human representations supports robust few-shot learning”,
2023.
[397] Muttenthaler, L., L. Linhardt, J. Dippel, et al.,
“Improving neural network representations using human
similarity judgments”, Neural information processing
systems, (2023).
[398] Muttenthaler, L., K. Greff, F. Born, et al., “Aligning
machine and human visual representations across abstraction
levels”, arXiv [cs.CV], 2024.
[399] Deng, J., W. Dong, R. Socher, L.-J. Li, K. Li, and L.
Fei-Fei, “ImageNet: A large-scale hierarchical
image database”, 2009 IEEE conference on computer
vision and pattern recognition, IEEE (2009), 248–255.
[400] Fellbaum, C., “WordNet and
wordnets”, In K. Brown, ed., Encyclopedia of
language and linguistics. Elsevier, 2005.
[401] Mehrer, J., C.J. Spoerer, E.C. Jones, N. Kriegeskorte, and
T.C. Kietzmann, “An ecologically motivated image dataset for
deep learning yields better models of human vision”,
Proc. Natl. Acad. Sci. U. S. A. 118(8), 2021,
pp. e2011417118.
[402] Huh, M., B. Cheung, T. Wang, and P. Isola, “The
platonic representation hypothesis”, arXiv
[cs.LG], 2024.
[403] Gauthaman, R.M., B. Ménard, and M.F. Bonner,
“Universal scale-free representations in human visual
cortex”, arXiv [q-bio.NC], 2024.
[404] Roads, B.D., and B.C. Love, “Enriching
ImageNet with human similarity judgments and
psychological embeddings”, 2021 IEEE/CVF conference on
computer vision and pattern recognition (CVPR), IEEE (2021).
[405] Hebart, M.N., O. Contier, L. Teichmann, et al.,
“THINGS-data, a multimodal collection of
large-scale datasets for investigating object representations in
human brain and behavior”, Elife 12,
2023.
[406] Borghesani, V., J. Armoza, M.N. Hebart, P. Bellec, and S.M.
Brambati, “The three terms task - an open benchmark to
compare human and artificial semantic representations”,
Sci Data 10(1), 2023, pp. 117.
[407] Peterson, J.C., R.M. Battleday, T.L. Griffiths, and O.
Russakovsky, “Human uncertainty makes classification more
robust”, arXiv [cs.CV], 2019.
[408] Xu, B., A. Bikakis, D. Onah, A. Vlachidis, and L. Dickens,
“Measuring error alignment for decision-making
systems”, arXiv [cs.AI], 2024.
[409] Klerke, S., Y. Goldberg, and A. Søgaard, “Improving
sentence compression by learning to predict gaze”,
arXiv [cs.CL], 2016.
[410] Ishibashi, T., Y. Sugano, and Y. Matsushita,
“Gaze-guided image classification for reflecting perceptual
class ambiguity”, Adjunct proceedings of the 31st
annual ACM symposium on user interface software and
technology, ACM (2018).
[411] Linsley, D., D. Shiebler, S. Eberhardt, and T. Serre,
“Learning what and where to attend”, arXiv
[cs.CV], 2018.
[412] Linsley, D., P. Feng, T. Boissin, et al., “Adversarial
alignment: Breaking the trade-off between the strength of an
attack and its relevance to human perception”, 2023.
[413] Lindsey, J.W., and S. Lippl, “Implicit regularization
of multi-task learning and finetuning in overparameterized neural
networks”, 2023.
[414] Itti, L., C. Koch, and E. Niebur, “A model of
saliency-based visual attention for rapid scene analysis”,
IEEE Trans. Pattern Anal. Mach. Intell. 20(11),
1998, pp. 1254–1259.
[415] Mathias, S., D. Kanojia, A. Mishra, and P. Bhattacharyya,
“A survey on using gaze behaviour for natural language
processing”, arXiv [cs.CL], 2021.
[416] Kiegeland, S., D.R. Reich, R. Cotterell, L.A. Jäger, and E.
Wilcox, “The pupil becomes the master: Eye-tracking feedback
for tuning LLMs”, ICML 2024 workshop on
LLMs and cognition, (2024).
[417] Hinton, G., O. Vinyals, and J. Dean, “Distilling the
knowledge in a neural network”, arXiv [stat.ML],
2015.
[418] Kriegeskorte, N., M. Mur, and P. Bandettini,
“Representational similarity analysis - connecting the
branches of systems neuroscience”, Front. Syst.
Neurosci. 2, 2008, pp. 4.
[419] Kornblith, S., M. Norouzi, H. Lee, and G. Hinton,
“Similarity of neural network representations
revisited”, International conference on machine
learning, PMLR (2019), 3519–3529.
[420] Xie, Y., A. Goyal, W. Zheng, et al., “Monte carlo tree
search boosts reasoning via iterative preference learning”,
arXiv [cs.AI], 2024.
[421] Fyshe, A., P.P. Talukdar, B. Murphy, and T.M. Mitchell,
“Interpretable semantic vectors from a joint model of brain-
and text-based meaning”, Proc. Conf. Assoc. Comput.
Linguist. Meet. 2014, 2014, pp. 489–499.
[422] Huth, A., S. Nishimoto, A. Vu, and J. Gallant, “A
continuous semantic space describes the representation of
thousands of object and action categories across the human
brain”, Neuron 76(6), 2012, pp.
1210–1224.
[423] Tang, J., A. LeBel, S. Jain, and A.G. Huth, “Semantic
reconstruction of continuous language from non-invasive brain
recordings”, 2022.
[424] Antonello, R., A. Vaidya, and A.G. Huth, “Scaling laws
for language encoding models in fMRI”, arXiv [cs.CL], 2023.
[425] Kohler, J., M.C. Ottenhoff, S. Goulis, et al.,
“Synthesizing speech from intracranial depth electrodes
using an encoder-decoder framework”, Neurons, Behavior,
Data analysis, and Theory, 2022.
[426] Moussa, O., D. Klakow, and M. Toneva, “Improving
semantic understanding in speech language models via
brain-tuning”, arXiv [cs.CL], 2024.
[427] Meek, A., A. Karpov, S.H. Cho, R. Koopmanschap, L. Farnik,
and B.-I. Cirstea, “Inducing human-like biases in moral
reasoning language models”, UniReps: 2nd edition of the
workshop on unifying representations in neural models,
(2024).
[428] Saxe, R., and N. Kanwisher, “People thinking about
thinking people. The role of the temporo-parietal junction in
‘theory of mind’”, Neuroimage
19(4), 2003, pp. 1835–1842.
[429] Sato, M., K. Tomeoka, I. Horiguchi, K. Arulkumaran, R.
Kanai, and S. Sasai, “Scaling law in neural data:
Non-invasive speech decoding with 175 hours of EEG
data”, arXiv [q-bio.NC], 2024.
[430] Allen, E.J., G. St-Yves, Y. Wu, et al., “A massive
7T fMRI dataset to bridge
cognitive neuroscience and artificial intelligence”,
Nat. Neurosci. 25(1), 2022, pp. 116–126.
[431] Freteault, M., M. Le Clei, L. Tetrel, P. Bellec, and N.
Farrugia, “Alignment of auditory artificial networks with
massive individual fMRI brain data
leads to generalizable improvements in brain encoding and
downstream tasks”, bioRxivorg, 2024.
[432] Ariely, D., and G.S. Berns, “Neuromarketing: The hope
and hype of neuroimaging in business”, Nat. Rev.
Neurosci. 11(4), 2010, pp. 284–292.
[433] Coupé, C., Y.M. Oh, D. Dediu, and F. Pellegrino,
“Different languages, similar encoding efficiency:
Comparable information rates across the human communicative
niche”, Sci. Adv. 5(9), 2019, pp.
eaaw2594.
[434] Zheng, J., and M. Meister, “The unbearable slowness of
being”, arXiv [q-bio.NC], 2024.
[435] Willett, F.R., D.T. Avansino, L.R. Hochberg, J.M. Henderson,
and K.V. Shenoy, “High-performance brain-to-text
communication via handwriting”, Nature
593(7858), 2021, pp. 249–254.
[436] Willett, F.R., E.M. Kunz, C. Fan, et al., “A
high-performance speech neuroprosthesis”, Nature
620(7976), 2023, pp. 1031–1036.
[437] Neuralink, “PRIME study progress update —
user experience”, 2024.
[438] Scotti, P.S., M. Tripathy, C.K.T. Villanueva, et al.,
“MindEye2: Shared-subject models enable fMRI-to-image with 1 hour of data”,
arXiv [cs.CV], 2024.
[439] Antonello, R., N. Sarma, J. Tang, J. Song, and A. Huth,
“How many bytes can you take out of brain-to-text
decoding?”, arXiv [cs.CL], 2024.
[440] Parthasarathy, N., J. Soetedjo, S. Panchavati, et al.,
“High performance P300 spellers using
GPT2 word prediction with cross-subject
training”, arXiv [cs.CL], 2024.
[441] Shi, N., Y. Miao, C. Huang, et al., “Estimating and
approaching the maximum information rate of noninvasive visual
brain-computer interface”, Neuroimage
289(120548), 2024, pp. 120548.
[442] Li, X., J. Chen, N. Shi, et al., “A hybrid
steady-state visual evoked response-based brain-computer interface
with MEG and EEG”, Expert
Syst. Appl. 223(119736), 2023, pp. 119736.
[443] Kernel, “Kernel flux and flow”, 2021.
[444] Tripathy, K., Z.E. Markow, A.K. Fishell, et al.,
“Decoding visual information from high-density diffuse
optical tomography neuroimaging data”, Neuroimage
226(117516), 2021, pp. 117516.
[445] Shin, J., J. Kwon, and C.-H. Im, “A ternary hybrid
EEG-NIRS brain-computer interface for
the classification of brain activation patterns during mental
arithmetic, motor imagery, and idle state”, Front.
Neuroinform. 12, 2018, pp. 5.
[446] Norman, S.L., D. Maresca, V.N. Christopoulos, et al.,
“Single-trial decoding of movement intentions using
functional ultrasound neuroimaging”, Neuron
109(9), 2021, pp. 1554–1566.e4.
[447] Jung, T., N. Zeng, J.D. Fabbri, et al., “Stable,
chronic in-vivo recordings from a fully wireless
subdural-contained 65,536-electrode brain-computer interface
device”, bioRxivorg, 2024, pp. 2024.05.17.594333.
[448] Allen, K.R., F. Brändle, M.M. Botvinick, et al.,
“Using games to understand the mind”, 2023.
[449] Spiers, H.J., A. Coutrot, and M. Hornberger,
“Explaining world-wide variation in navigation ability from
millions of people: Citizen science project sea hero
quest”, Top. Cogn. Sci. 15(1), 2023, pp.
120–138.
[450] Devlin, S., R. Georgescu, I. Momennejad, et al.,
“Navigation turing test (NTT): Learning to
evaluate human-like navigation”, 2021.
[451] Cross, L., J. Cockburn, Y. Yue, and J.P. O’Doherty,
“Using deep reinforcement learning to reveal how the brain
encodes abstract state-space representations in high-dimensional
environments”, Neuron 109(4), 2021, pp.
724–738.e7.
[452] Kemtur, A., F. Paugam, B. Pinsard, et al., “Behavioral
imitation with artificial neural networks leads to personalized
models of brain dynamics during videogame play”,
bioRxiv, 2023, pp. 2023.10.28.564546.
[453] Zhang, T., “Modelling navigation representations
during naturalistic driving”, 2021.
[454] Hafner, D., J. Pasukonis, J. Ba, and T. Lillicrap,
“Mastering diverse domains through world models”,
2023.
[455] Bard, N., J.N. Foerster, S. Chandar, et al., “The
hanabi challenge: A new frontier for AI
research”, arXiv [cs.LG], 2019.
[456] Brown, N., A. Bakhtin, A. Lerer, and Q. Gong,
“Combining deep reinforcement learning and search for
imperfect-information games”, arXiv [cs.GT], 2020.
[457] Pan, A., J.S. Chan, A. Zou, et al., “Do the rewards
justify the means? Measuring trade-offs between rewards and
ethical behavior in the MACHIAVELLI
benchmark”, arXiv [cs.LG], 2023.
[458] Marblestone, A.H., G. Wayne, and K.P. Kording, “Toward
an integration of deep learning and neuroscience”,
Front. Comput. Neurosci. 10, 2016, pp. 94.
[459] Arora, S., and P. Doshi, “A survey of inverse
reinforcement learning: Challenges, methods and progress”,
arXiv [cs.LG], 2018.
[460] Sarma, G., and N.J. Hay, “Mammalian value
systems”, Informatica (Vilnius)
abs/1607.08289(4), 2016.
[461] Sarma, G.P., N.J. Hay, and A. Safron, “AI
safety and reproducibility: Establishing robust foundations for
the neuropsychology of human values”, In Developments
in language theory. Springer International Publishing, Cham,
2018, 507–512.
[462] Collins, K.M., I. Sucholutsky, U. Bhatt, et al.,
“Building machines that learn and think with people”,
arXiv [cs.HC], 2024.
[463] Yamins, D.L.K., and J.J. DiCarlo, “Using goal-driven
deep learning models to understand sensory cortex”,
Nat. Neurosci. 19(3), 2016, pp. 356–365.
[464] Doerig, A., R. Sommers, K. Seeliger, et al., “The
neuroconnectionist research programme”, 2022.
[465] Yamins, D.L.K., H. Hong, C.F. Cadieu, E.A. Solomon, D.
Seibert, and J.J. DiCarlo, “Performance-optimized
hierarchical models predict neural responses in higher visual
cortex”, Proceedings of the national academy of
sciences 111(23), 2014, pp. 8619–8624.
[466] Khaligh-Razavi, S.-M., and N. Kriegeskorte, “Deep
supervised, but not unsupervised, models may explain
IT cortical representation”, PLoS Comput.
Biol. 10(11), 2014, pp. e1003915.
[467] Sussillo, D., M.M. Churchland, M.T. Kaufman, and K.V.
Shenoy, “A neural network that finds a naturalistic solution
for the production of muscle activity”, Nat.
Neurosci. 18(7), 2015, pp. 1025–1033.
[468] Mineault, P., S. Bakhtiari, B. Richards, and C. Pack,
“Your head is there to move you around: Goal-driven models
of the primate dorsal pathway”, Neural information
processing systems (NeurIPS), (2021).
[469] Nayebi, A., R. Rajalingham, M. Jazayeri, and G.R. Yang,
“Neural foundations of mental simulation: Future prediction
of latent representations on dynamic scenes”, Neural
information processing systems, (2023).
[470] Conwell, C., J.S. Prince, K.N. Kay, G.A. Alvarez, and T.
Konkle, “What can 1.8 billion regressions tell us about the
pressures shaping high-level visual representation in brains and
machines?”, 2022.
[471] Conwell, C., J.S. Prince, K.N. Kay, G.A. Alvarez, and T.
Konkle, “A large-scale examination of inductive biases
shaping high-level visual representation in brains and
machines”, Nat. Commun. 15(1), 2024, pp.
9383.
[472] Rideaux, R., and A.E. Welchman, “But still it moves:
Static image statistics underlie how we see motion”,
Journal of Neuroscience 40(12), 2020, pp.
2538–2552.
[473] Bakhtiari, S., P. Mineault, T. Lillicrap, C. Pack, and B.
Richards, “The functional specialization of visual cortex
emerges from training parallel pathways with self-supervised
predictive learning”, Neural information processing
systems (NeurIPS), (2021).
[474] Vafaii, H., J. Yates, and D. Butts, “Hierarchical
VAEs provide a normative account of motion processing
in the primate brain”, Neural information processing
systems, (2023).
[475] Chang, L., B. Egger, T. Vetter, and D.Y. Tsao,
“Explaining face representation in the primate brain using
different computational models”, Curr. Biol.
31(13), 2021, pp. 2785–2795.e4.
[476] Bonner, M.F., and R.A. Epstein, “Object
representations in the human brain reflect the co-occurrence
statistics of vision and language”, Nat. Commun.
12(1), 2021, pp. 4081.
[477] Lindsay, G.W., and K.D. Miller, “How biological
attention mechanisms improve task performance in a large-scale
visual system model”, Elife 7, 2018.
[478] Lotter, W., G. Kreiman, and D. Cox, “A neural network
trained for prediction mimics diverse features of biological
neurons and perception”, Nat Mach Intell
2(4), 2020, pp. 210–219.
[479] Hannagan, T., A. Agrawal, L. Cohen, and S. Dehaene,
“Emergence of a compositional neural code for written words:
Recycling of a convolutional neural network for reading”,
Proceedings of the National Academy of Sciences
118(46), 2021.
[480] Kell, A.J.E., D.L.K. Yamins, E.N. Shook, S.V.
Norman-Haignere, and J.H. McDermott, “A task-optimized
neural network replicates human auditory behavior, predicts brain
responses, and reveals a cortical processing hierarchy”,
Neuron 98(3), 2018, pp. 630–644.
[481] Francl, A., and J.H. McDermott, “Deep neural network
models of sound localization reveal how perception is adapted to
real-world environments”, Nat. Hum. Behav.
6(1), 2022, pp. 111–133.
[482] Caucheteux, C., and J.-R. King, “Brains and algorithms
partially converge in natural language processing”,
Commun Biol 5(1), 2022, pp. 1–10.
[483] Fedorenko, E., I.A. Blank, M. Siegelman, and Z. Mineroff,
“Lack of selectivity for syntax relative to word meanings
throughout the language network”, Cognition
203(104348), 2020, pp. 104348.
[484] Caucheteux, C., A. Gramfort, and J.-R. King, “Evidence
of a predictive coding hierarchy in the human brain listening to
speech”, Nat Hum Behav, 2023, pp. 1–12.
[485] Schrimpf, M., I.A. Blank, G. Tuckute, et al., “The
neural architecture of language: Integrative modeling converges on
predictive processing”, Proceedings of the National
Academy of Sciences 118(45), 2021, pp. e2105646118.
[486] Rajan, K., C.D. Harvey, and D.W. Tank, “Recurrent
network models of sequence generation and memory”,
Neuron 90(1), 2016, pp. 128–142.
[487] Pandarinath, C., P. Nuyujukian, C.H. Blabe, et al.,
“High performance communication by people with paralysis
using an intracortical brain-computer interface”,
Elife 6, 2017, pp. e18554.
[488] Russo, A.A., R. Khajeh, S.R. Bittner, et al., “Neural
trajectories in the supplementary motor area and motor cortex
exhibit distinct geometries, compatible with different classes of
computation”, Neuron 107(4), 2020, pp.
745–758.e6.
[489] Dasgupta, S., C.F. Stevens, and S. Navlakha, “A neural
algorithm for a fundamental computing problem”,
Science 358(6364), 2017, pp. 793–796.
[490] Wang, P.Y., Y. Sun, R. Axel, L.F. Abbott, and G.R. Yang,
“Evolving the olfactory system with machine
learning”, bioRxiv, 2021, pp. 2021.04.15.439917.
[491] Taleb, F., M.S. Vasco, N. Rajabi, M. Björkman, and D.
Kragic, “Can foundation models smell like humans?”,
(2024).
[492] Banino, A., C. Barry, B. Uria, et al., “Vector-based
navigation using grid-like representations in artificial
agents”, Nature 557(7705), 2018, pp.
429–433.
[493] Cueva, C.J., and X.-X. Wei, “Emergence of grid-like
representations by training recurrent neural networks to perform
spatial localization”, arXiv [q-bio.NC], 2018.
[494] Whittington, J.C.R., T.H. Muller, S. Mark, et al.,
“The tolman-eichenbaum machine: Unifying space and
relational memory through generalization in the hippocampal
formation”, Cell 183(5), 2020, pp.
1249–1263.e23.
[495] Nayebi, A., A. Attinger, M.G. Campbell, et al.,
“Explaining heterogeneity in medial entorhinal cortex with
task-driven neural networks”, 2021.
[496] Sorscher, B., G.C. Mel, S.A. Ocko, L.M. Giocomo, and S.
Ganguli, “A unified theory for the computational and
mechanistic origins of grid cells”, Neuron
111(1), 2023, pp. 121–137.e13.
[497] Stachenfeld, K.L., M.M. Botvinick, and S.J. Gershman,
“The hippocampus as a predictive map”, Nat.
Neurosci. 20(11), 2017, pp. 1643–1653.
[498] Fang, C., D. Aronov, L. Abbott, and E.L. Mackevicius,
“Neural learning rules for generating flexible predictions
and computing the successor representation”, elife
12, 2023, pp. e80680.
[499] George, T.M., K. Stachenfeld, C. Barry, C. Clopath, and T.
Fukai, “A generative model of the hippocampal formation
trained with theta driven local learning rules”, Neural
information processing systems, (2023).
[500] Bono, J., S. Zannone, V. Pedrosa, and C. Clopath,
“Learning predictive cognitive maps with spiking neurons
during behavior and replays”, Elife 12,
2023, pp. e80671.
[501] Whittington, J.C.R., J. Warren, and T.E.J. Behrens,
“Relating transformers to models and neural representations
of the hippocampal formation”, arXiv [cs.NE],
2021.
[502] Jensen, K.T., G. Hennequin, and M.G. Mattar, “A
recurrent network model of planning explains hippocampal replay
and human behavior”, Nat. Neurosci.
27(7), 2024, pp. 1340–1348.
[503] Mante, V., D. Sussillo, K.V. Shenoy, and W.T. Newsome,
“Context-dependent computation by recurrent dynamics in
prefrontal cortex”, Nature 503(7474),
2013, pp. 78–84.
[504] Wang, J.X., Z. Kurth-Nelson, D. Kumaran, et al.,
“Prefrontal cortex as a meta-reinforcement learning
system”, Nat. Neurosci. 21(6), 2018, pp.
860–868.
[505] Yang, G.R., M.R. Joglekar, H.F. Song, W.T. Newsome, and
X.-J. Wang, “Task representations in neural networks trained
to perform many cognitive tasks”, Nat. Neurosci.
22(2), 2019, pp. 297–306.
[506] Summerfield, C., F. Luyckx, and H. Sheahan, “Structure
learning and the posterior parietal cortex”, Prog.
Neurobiol. 184, 2020, pp. 101717.
[507] Fedorenko, E., S.T. Piantadosi, and E.A.F. Gibson,
“Language is primarily a tool for communication rather than
thought”, Nature 630(8017), 2024, pp.
575–586.
[508] Berrios, W., and A. Deza, Joint rotational invariance
and adversarial training of a dual-stream transformer yields state
of the art brain-score for area V4, arXiv, 2022.
[509] Schrimpf, M., J. Kubilius, H. Hong, et al.,
“Brain-score: Which artificial neural network for object
recognition is most brain-like?”, BioRxiv, 2018,
pp. 407007.
[510] Linsley, D., I.F.R. Rodriguez, T. Fel, et al.,
“Performance-optimized deep neural networks are evolving
into worse models of inferotemporal visual cortex”,
Neural information processing systems, (2023).
[511] Gokce, A., and M. Schrimpf, “Scaling laws for
task-optimized models of the primate visual ventral
stream”, arXiv [cs.LG], 2024.
[512] Chen, Z., and M.F. Bonner, “Universal dimensions of
visual representation”, 2024.
[513] Antonello, R., and A. Huth, “Predictive coding or just
feature discovery? An alternative account of why language models
fit brain data”, Neurobiol. Lang. (Camb.)
5(1), 2024, pp. 64–79.
[514] Sexton, N.J., and B.C. Love, “Reassessing hierarchical
correspondences between brain and deep networks through direct
interface”, Science Advances 8(28), 2022,
pp. eabm2219.
[515] Soni, A., S. Srivastava, M. Khosla, and K.P. Kording,
“Conclusions about neural network to brain alignment are
profoundly impacted by the similarity measure”,
bioRxiv, 2024, pp. 2024.08.07.607035.
[516] Thobani, I., J. Sagastuy-Brena, A. Nayebi, R. Cao, and
D.L.K. Yamins, “Inter-animal transforms as a guide to
model-brain comparison”, ICLR 2024 workshop on
representational alignment, (2024).
[517] Ahlert, J., T. Klein, F.A. Wichmann, and R. Geirhos,
“How aligned are different alignment metrics?”,
(2024).
[518] Klabunde, M., T. Wald, T. Schumacher, K. Maier-Hein, M.
Strohmaier, and F. Lemmerich, “ReSi: A
comprehensive benchmark for representational similarity
measures”, arXiv [cs.LG], 2024.
[519] Elmoznino, E., and M.F. Bonner, “High-performing
neural network models of visual cortex benefit from high latent
dimensionality”, 2022.
[520] Schaeffer, R., M. Khona, S. Chandra, M. Ostrow, B. Miranda,
and S. Koyejo, “Position: Maximizing neural regression
scores may not identify good models of the brain”,
UniReps: 2nd edition of the workshop on unifying
representations in neural models, (2024).
[521] Zednik, C., and F. Jäkel, “Bayesian
reverse-engineering considered as a research strategy for
cognitive science”, Synthese 193(12),
2016, pp. 3951–3985.
[522] Golan, T., P.C. Raju, and N. Kriegeskorte,
“Controversial stimuli: Pitting neural networks against each
other as models of human cognition”, Proc. Natl. Acad.
Sci. U. S. A. 117(47), 2020, pp. 29330–29337.
[523] Tuckute, G., D. Finzi, E. Margalit, et al., “How to
optimize neuroscience data utilization and experiment design for
advancing primate visual and linguistic brain models?”,
arXiv [q-bio.NC], 2024.
[524] Olshausen, B.A., and D.J. Field, “Emergence of
simple-cell receptive field properties by learning a sparse code
for natural images”, Nature 381, 1996,
pp. 607–609.
[525] Rao, R.P.N., and D.H. Ballard, “Predictive coding in
the visual cortex: A functional interpretation of some
extra-classical receptive-field effects”, Nat.
Neurosci. 2(1), 1999, pp. 79–87.
[526] Agrawal, K.K., A.K. Mondal, A. Ghosh, and B.A. Richards,
“\(\alpha\)-ReQ : Assessing
representation quality in self-supervised learning by measuring
eigenspectrum decay”, (2022).
[527] Northcutt, C.G., L. Jiang, and I.L. Chuang, “Confident
learning: Estimating uncertainty in dataset labels”,
arXiv [stat.ML], 2019.
[528] Caballero, E., K. Gupta, I. Rish, and D. Krueger,
“Broken neural scaling laws”, 2022.
[529] Kandasamy, K., W. Neiswanger, J. Schneider, B. Poczos, and
E.P. Xing, “Neural architecture search with bayesian
optimisation and optimal transport”, Advances in Neural
Information Processing Systems 31, 2018.
[530] Schultz, W., P. Dayan, and P.R. Montague, “A neural
substrate of prediction and reward”, Science
275(5306), 1997, pp. 1593–1599.
[531] Hassabis, D., D. Kumaran, C. Summerfield, and M. Botvinick,
“Neuroscience-inspired artificial intelligence”,
Neuron 95(2), 2017, pp. 245–258.
[532] Lindsay, G., Models of the mind: How physics,
engineering and mathematics have shaped our understanding of the
brain, Bloomsbury Sigma, 1. Aufl, 2021.
[533] Schultz, W., “Reward functions of the basal
ganglia”, J. Neural Transm. 123(7), 2016,
pp. 679–693.
[534] Pessiglione, M., B. Seymour, G. Flandin, R.J. Dolan, and
C.D. Frith, “Dopamine-dependent prediction errors underpin
reward-seeking behaviour in humans”, Nature
442(7106), 2006, pp. 1042–1045.
[535] Huys, Q.J.M., T.V. Maia, and M.J. Frank,
“Computational psychiatry as a bridge from neuroscience to
clinical applications”, Nat. Neurosci.
19(3), 2016, pp. 404–413.
[536] Lee, S.W., S. Shimojo, and J.P. O’Doherty, “Neural
computations underlying arbitration between model-based and
model-free learning”, Neuron 81(3), 2014,
pp. 687–699.
[537] Lowet, A.S., Q. Zheng, S. Matias, J. Drugowitsch, and N.
Uchida, “Distributional reinforcement learning in the
brain”, Trends Neurosci. 43(12), 2020,
pp. 980–997.
[538] Muller, T.H., J.L. Butler, S. Veselic, et al.,
“Distributional reinforcement learning in prefrontal
cortex”, Nat. Neurosci. 27(3), 2024, pp.
403–408.
[539] Lee, R.S., Y. Sagiv, B. Engelhard, I.B. Witten, and N.D.
Daw, “A feature-specific prediction error model explains
dopaminergic heterogeneity”, Nat. Neurosci.
27(8), 2024, pp. 1574–1586.
[540] Barto, A., R.L. Lewis, and S. Singh, “Where do rewards
come from”, 31, 2009.
[541] Keramati, M., and B. Gutkin, “Homeostatic
reinforcement learning for integrating reward collection and
physiological stability”, Elife 3, 2014.
[542] Juechems, K., and C. Summerfield, “Where does value
come from?”, Trends Cogn. Sci. 23(10),
2019, pp. 836–850.
[543] Millidge, B., M. Walton, and R. Bogacz, “Reward bases:
Instantaneous reward revaluation with temporal difference
learning”, bioRxiv, 2022, pp. 2022.04.14.488361.
[544] Weber, L., D.M. Yee, D.M. Small, and F.H. Petzschner,
“Rethinking reinforcement learning: The interoceptive origin
of reward”, PsyArXiv, 2024.
[545] Li, F., J.W. Lindsey, E.C. Marin, et al., “The
connectome of the adult drosophila mushroom body provides insights
into function”, Elife 9, 2020.
[547] Allsop, S.A., R. Wichmann, F. Mills, et al.,
“Corticoamygdala transfer of socially derived information
gates observational learning”, Cell
173(6), 2018, pp. 1329–1342.
[548] Kohl, J., B.M. Babayan, N.D. Rubinstein, et al.,
“Functional circuit architecture underlying parental
behaviour”, Nature 556(7701), 2018, pp.
326–331.
[549] Dabney, W., Z. Kurth-Nelson, N. Uchida, et al., “A
distributional code for value in dopamine-based reinforcement
learning”, Nature 577(7792), 2020, pp.
671–675.
[550] Byrnes, S., “Dopamine-supervised learning in mammals
& fruit flies”, 2021. https://www.lesswrong.com/posts/GnmLReqNrP4CThn6/dopamine-supervised-learning-in-mammals-and-fruit-flies
[551] Sutton, R.S., and A.G. Barto, Reinforcement learning: An
introduction, MIT press, 2018.
[552] Morris, M.J., J.E. Beilharz, J. Maniam, A.C. Reichelt, and
R.F. Westbrook, “Why is obesity such a problem in the
21st century? The intersection of palatable food,
cues and reward pathways, stress, and cognition”,
Neurosci. Biobehav. Rev. 58, 2015, pp. 36–45.
[553] Ulrich, M., A. Rüger, V. Durner, G. Grön, and H. Graf,
“Reward is not reward: Differential impacts of primary and
secondary rewards on expectation, outcome, and prediction error in
the human brain’s reward processing regions”,
Neuroimage 283(120440), 2023, pp. 120440.
[554] Markman, M., E. Saruco, S. Al-Bas, et al.,
“Differences in discounting behavior and brain responses for
food and money reward”, eNeuro 11(4),
2024.
[555] Gadagkar, V., P.A. Puzerey, R. Chen, E. Baird-Daniel, A.R.
Farhang, and J.H. Goldberg, “Dopamine neurons encode
performance error in singing birds”, Science
354(6317), 2016, pp. 1278–1282.
[556] Duffy, A., K.W. Latimer, J.H. Goldberg, A.L. Fairhall, and
V. Gadagkar, “Dopamine neurons evaluate natural fluctuations
in performance quality”, Cell reports
38(13), 2022.
[557] Roeser, A., V. Gadagkar, A. Das, P.A. Puzerey, B. Kardon,
and J.H. Goldberg, “Dopaminergic error signals retune to
social feedback during courtship”, Nature
623(7986), 2023, pp. 375–380.
[558] Mandelblat-Cerf, Y., L. Las, N. Denisenko, and M.S. Fee,
“A role for descending auditory cortical projections in
songbird vocal learning”, Elife 3, 2014.
[559] Hisey, E., M.G. Kearney, and R. Mooney, “A common
neural circuit mechanism for internally guided and externally
reinforced forms of motor learning”, Nature
neuroscience 21(4), 2018, pp. 589–597.
[560] Kearney, M.G., T.L. Warren, E. Hisey, J. Qi, and R. Mooney,
“Discrete evaluative and premotor circuits enable vocal
learning in songbirds”, Neuron 104(3),
2019, pp. 559–575.
[561] Roberts, T.F., S.M. Gobes, M. Murugan, B.P. Ölveczky, and R.
Mooney, “Motor circuits are required to encode a sensory
model for imitative learning”, Nature neuroscience
15(10), 2012, pp. 1454–1459.
[562] Mackevicius, E.L., and M.S. Fee, “Building a state
space for song learning”, Curr. Opin. Neurobiol.
49, 2018, pp. 59–68.
[563] Kanoski, S.E., M.R. Hayes, and K.P. Skibicka,
“GLP-1 and weight loss: Unraveling the diverse
neural circuitry”, Am. J. Physiol. Regul. Integr. Comp.
Physiol. 310(10), 2016, pp. R885–95.
[564] Ng, A.Y., and S. Russell, “Algorithms for inverse
reinforcement learning”, ICML 67, 2000,
pp. 663–670.
[565] Rothkopf, C.A., and D.H. Ballard, “Modular inverse
reinforcement learning for visuomotor behavior”, Biol.
Cybern. 107(4), 2013, pp. 477–490.
[566] Yamaguchi, S., H. Naoki, M. Ikeda, et al.,
“Identification of animal behavioral strategies by inverse
reinforcement learning”, PLoS Comput. Biol.
14(5), 2018, pp. e1006122.
[567] Jara-Ettinger, J., “Theory of mind as inverse
reinforcement learning”, Curr. Opin. Behav. Sci.
29, 2019, pp. 105–110.
[568] Tan, J., X. Shen, X. Zhang, Z. Song, and Y. Wang,
“Estimating reward function from medial prefrontal cortex
cortical activity using inverse reinforcement learning”,
Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2022,
2022, pp. 3346–3349.
[569] Kalweit, G., M. Kalweit, M. Alyahyay, et al.,
“NeuRL: Closed-form inverse reinforcement
learning for neural decoding”, arXiv [q-bio.NC],
2022.
[570] Ashwood, Z.C., A. Jha, and J.W. Pillow, “Dynamic
inverse reinforcement learning for characterizing animal
behavior”, Neural Inf Process Syst, 2022.
[571] Gong, J., S. Cao, S. Korivand, and N. Jalili,
“Reconstructing human gaze behavior from EEG
using inverse reinforcement learning”, Smart
Health 32(100480), 2024, pp. 100480.
[572] Lee, S.H., M.-H. Oh, and W.-Y. Ahn, “Inverse
reinforcement learning captures value representations in the
reward circuit in a real-time driving task: A preliminary
study”, (2024).
[573] Urbaniak, R., M. Xie, and E. Mackevicius, “Linking
cognitive strategy, neural mechanism, and movement statistics in
group foraging behaviors”, Sci. Rep.
14(1), 2024, pp. 21770.
[574] Davidson, G., G. Todd, J. Togelius, T.M. Gureckis, and B.M.
Lake, “Goals as reward-producing programs”, 2024. https://arxiv.org/abs/2405.13242
[575] Cisek, P., “Resynthesizing behavior through
phylogenetic refinement”, Atten. Percept.
Psychophys. 81(7), 2019, pp. 2265–2287.
[576] Karin, O., and U. Alon, “The dopamine circuit as a
reward-taxis navigation system”, PLoS Comput.
Biol. 18(7), 2022, pp. e1010340.
[577] Yao, Z., C.T. van Velthoven, M. Kunst, et al., “A
high-resolution transcriptomic and spatial atlas of cell types in
the whole mouse brain”, Nature 624(7991),
2023, pp. 317–332.
[578] Barack, D.L., and J.W. Krakauer, “Two views on the
cognitive brain”, Nat. Rev. Neurosci., 2021, pp.
1–13.
[579] Räuker, T., A. Ho, S. Casper, and D. Hadfield-Menell,
“Toward transparent AI: A survey on
interpreting the inner structures of deep neural networks”,
2023.
[580] Bereska, L., and E. Gavves, “Mechanistic
interpretability for AI safety – a review”,
2024.
[581] Olah, C., N. Cammarata, L. Schubert, G. Goh, M. Petrov, and
S. Carter, “Zoom in: An introduction to circuits”,
Distill 5(3), 2020, pp. e00024.001.
[582] Elhage, N., N. Nanda, C. Olsson, et al., “A
mathematical framework for transformer circuits”,
Transformer Circuits Thread, 2021.
[583] Zou, A., L. Phan, S. Chen, et al., “Representation
engineering: A top-down approach to AI
transparency”, arXiv [cs.LG], 2023.
[584] Nanda, N., “A longlist of theories of impact for
interpretability”, 2022.
[585] Goh, G., †N.C., †C.V., et al., “Multimodal neurons in
artificial neural networks”, Distill, 2021.
[586] Burns, C., H. Ye, D. Klein, and J. Steinhardt,
“Discovering latent knowledge in language models without
supervision”, 2024.
[587] Turner, A.M., L. Thiergart, G. Leech, et al.,
“Activation addition: Steering language models without
optimization”, 2024.
[588] Bau, D., J.-Y. Zhu, H. Strobelt, et al.,
“GAN dissection: Visualizing and understanding
generative adversarial networks”, 2018.
[589] Meng, K., D. Bau, A. Andonian, and Y. Belinkov,
“Locating and editing factual associations in
GPT”, 2023.
[590] Thompson, J.A.F., “Forms of explanation and
understanding for neuroscience and artificial
intelligence”, J. Neurophysiol. 126(6),
2021, pp. 1860–1874.
[591] Jonas, E., and K.P. Kording, “Could a neuroscientist
understand a microprocessor?”, PLoS Comput. Biol.
13(1), 2017, pp. e1005268.
[592] Lillicrap, T.P., and K.P. Kording, “What does it mean
to understand a neural network?”, arXiv [cs.LG],
2019.
[593] Olah, C., “Interpretability vs neuroscience”,
2021.
[594] Kar, K., S. Kornblith, and E. Fedorenko,
“Interpretability of artificial neural network models in
artificial intelligence vs. neuroscience”, Nat Mach
Intell 4(12), 2022, pp. 1065–1067.
[595] Shan Xu, C., M. Januszewski, Z. Lu, et al., “A
connectome of the adult drosophila central brain”,
bioRxiv, 2020, pp. 2020.01.21.911859.
[596] Scheffer, L.K., C.S. Xu, M. Januszewski, et al., “A
connectome and analysis of the adult drosophila central
brain”, Elife 9, 2020.
[597] Nguyen, J.P., F.B. Shipley, A.N. Linder, et al.,
“Whole-brain calcium imaging with cellular resolution in
freely behaving caenorhabditis elegans”, Proc. Natl.
Acad. Sci. U. S. A. 113(8), 2016, pp. E1074–81.
[598] Aimon, S., T. Katsuki, T. Jia, et al., “Fast
near-whole brain imaging in adult drosophila during responses to
stimuli and behavior”, bioRxiv, 2018, pp. 033803.
[599] Lad, V., W. Gurnee, and M. Tegmark, “The remarkable
robustness of LLMs: Stages of inference?”,
arXiv [cs.LG], 2024.
[600] Shin, H., M.B. Ogando, L. Abdeladim, et al.,
“Recurrent pattern completion drives the neocortical
representation of sensory inference”, 2023.
[601] Adesnik, H., and L. Abdeladim, “Probing neural codes
with two-photon holographic optogenetics”, Nat.
Neurosci. 24(10), 2021, pp. 1356–1366.
[602] Shadlen, M.N., and W.T. Newsome, “The variable
discharge of cortical neurons: Implications for connectivity,
computation, and information coding”, J. Neurosci.
18(10), 1998, pp. 3870–3896.
[603] Watanakeesuntorn, W., K. Takahashi, K. Ichikawa, et al.,
“Massively parallel causal inference of whole brain dynamics
at single neuron resolution”, 2020.
[604] Vyas, S., M.D. Golub, D. Sussillo, and K.V. Shenoy,
“Computation through neural population dynamics”,
Annu. Rev. Neurosci. 43(1), 2020, pp. 249–275.
[605] Maheswaranathan, N., A. Williams, M. Golub, S. Ganguli, and
D. Sussillo, “Reverse engineering recurrent networks for
sentiment classification reveals line attractor dynamics”,
Adv. Neural Inf. Process. Syst. 32, 2019.
[606] Vaswani, A., N. Shazeer, N. Parmar, et al., “Attention
is all you need”, 2017.
[607] Dutta, S., T. Gautam, S. Chakrabarti, and T. Chakraborty,
“Redesigning the transformer architecture with insights from
multi-particle dynamical systems”, arXiv [cs.LG],
2021.
[608] Beck, M., K. Pöppel, M. Spanring, et al., “xLSTM: Extended long short-term
memory”, arXiv [cs.LG], 2024.
[609] Dao, T., and A. Gu, “Transformers are
SSMs: Generalized models and efficient algorithms
through structured state space duality”, arXiv
[cs.LG], 2024.
[610] Elhage, N., T. Hume, C. Olsson, et al., “Toy models of
superposition”, Transformer Circuits Thread, 2022.
[611] Barak, O., M. Rigotti, and S. Fusi, “The sparseness of
mixed selectivity neurons controls the
generalization-discrimination trade-off”, J.
Neurosci. 33(9), 2013, pp. 3844–3856.
[612] Meunier, D., R. Lambiotte, and E.T. Bullmore, “Modular
and hierarchically modular organization of brain networks”,
Front. Neurosci. 4, 2010, pp. 200.
[613] Bonhoeffer, T., and A. Grinvald, “Iso-orientation
domains in cat visual cortex are arranged in pinwheel-like
patterns”, Nature 353, 1991, pp. 429–431.
[614] Tanaka, K., “Columns for complex visual object
features in the inferotemporal cortex: Clustering of cells with
similar but slightly different stimulus selectivities”,
Cereb. Cortex 13(1), 2003, pp. 90–99.
[615] Paik, S.-B., and D.L. Ringach, “Retinal origin of
orientation maps in visual cortex”, Nat. Neurosci.
14(7), 2011, pp. 919–925.
[616] Ringach, D.L., P.J. Mineault, E. Tring, N.D. Olivas, P.
Garcia-Junco-Clemente, and J.T. Trachtenberg, “Spatial
clustering of tuning in mouse primary visual cortex”,
Nat. Commun. 7(1), 2016, pp. 12270.
[617] Voss, C., G. Goh, N. Cammarata, M. Petrov, L. Schubert, and
C. Olah, “Branch specialization”, Distill
6(4), 2021.
[618] Achterberg, J., D. Akarca, D.J. Strouse, J. Duncan, and D.E.
Astle, “Spatially-embedded recurrent neural networks reveal
widespread links between structural and functional neuroscience
findings”, 2022.
[619] Kumar, S., T.R. Sumers, T. Yamakoshi, et al., “Shared
functional specialization in transformer-based language models and
the human brain”, Nat. Commun. 15(1),
2024, pp. 5523.
[620] Dobzhansky, T., “Nothing in biology makes sense except
in the light of evolution”, Am. Biol. Teach.
35(3), 1973, pp. 125–129.
[621] Kaznatcheev, A., and K.P. Kording, “Nothing makes
sense in deep learning, except in the light of evolution”,
2022.
[622] Mordvintsev, A., E. Randazzo, E. Niklasson, M. Levin, and S.
Greydanus, “Thread: Differentiable self-organizing
systems”, Distill, 2020.
[623] Stanley, K.O., J. Clune, J. Lehman, and R. Miikkulainen,
“Designing neural networks through neuroevolution”,
Nat. Mach. Intell. 1(1), 2019, pp. 24–35.
[624] Sherrington, C.S., The integrative action of the nervous
system, Yale University Press, New Haven, CT, US, 1906.
[625] Hartline, H.K., “The receptive fields of optic nerve
fibers”, Am. J. Physiol. 130(4), 1940,
pp. 690–699.
[626] De Boer, E., and P. Kuyper, “Triggered
correlation”, IEEE Transactions on Biomedical
Engineering(3), 1968, pp. 169–179.
[627] Marmarelis, P.Z., and V.Z. Marmarelis, Analysis of
physiological systems: The white-noise approach, Plenum Press
New York, 1978.
[628] Ringach, D.L., “Mapping receptive fields in primary
visual cortex”, J. Physiol. 558(Pt 3),
2004, pp. 717–728.
[629] Schwartz, O., J.W. Pillow, N.C. Rust, and E.P. Simoncelli,
“Spike-triggered neural characterization”, J.
Vis. 6(4), 2006.
[630] Berkes, P., and L. Wiskott, “Analysis and
interpretation of quadratic models of receptive fields”,
Nat. Protoc. 2(2), 2007, pp. 400–407.
[631] Paninski, L., “Maximum likelihood estimation of
cascade point-process neural encoding models”, Network:
Computation in Neural Systems 15(4), 2004, pp.
243–262.
[632] McFarland, J.M., Y. Cui, and D.A. Butts, “Inferring
nonlinear neuronal computation based on physiologically plausible
inputs”, PLoS Comput. Biol. 9(7), 2013,
pp. e1003143.
[633] Wu, A., I.-S. Park, and J.W. Pillow, “Convolutional
spike-triggered covariance analysis for neural subunit
models”, Adv. Neural Inf. Process. Syst., 2015,
pp. 793–801.
[634] McIntosh, L.T., N. Maheswaranathan, A. Nayebi, S. Ganguli,
and S.A. Baccus, “Deep learning models of the retinal
response to natural scenes”, Adv. Neural Inf. Process.
Syst. 29, 2016, pp. 1369–1377.
[635] Cadena, S.A., F.H. Sinz, T. Muhammad, et al., “How
well do deep neural networks trained on object recognition
characterize the mouse visual system?”, 2019.
[636] Gosselin, F., and P.G. Schyns, “Bubbles: A technique
to reveal the use of information in recognition tasks”,
Vision Res. 41(17), 2001, pp. 2261–2271.
[637] Hubel, D.H., and T.N. Wiesel, “Receptive fields and
functional architecture of monkey striate cortex”, J.
Physiol. 195(1), 1968, pp. 215–243.
[638] Butts, D.A., and M.S. Goldman, “Tuning curves,
neuronal variability, and sensory coding”, PLoS
Biol. 4(4), 2006, pp. e92.
[639] DiMattina, C., and K. Zhang, “Adaptive stimulus
optimization for sensory systems neuroscience”, Front.
Neural Circuits 7, 2013, pp. 101.
[640] Feather, J., G. Leclerc, A. Mądry, and J.H. McDermott,
“Model metamers reveal divergent invariances between
biological and artificial neural networks”, Nat.
Neurosci., 2023, pp. 1–18.
[641] Gold, J.I., and M.N. Shadlen, “The neural basis of
decision making”, Annu. Rev. Neurosci.
30, 2007, pp. 535–574.
[642] Cohen, M.R., and W.T. Newsome, “Estimates of the
contribution of single neurons to perception depend on timescale
and noise correlation”, J. Neurosci.
29(20), 2009, pp. 6635–6648.
[643] Bernstein, J.G., P.A. Garrity, and E.S. Boyden,
“Optogenetics and thermogenetics: Technologies for
controlling the activity of targeted cells within intact neural
circuits”, Curr. Opin. Neurobiol. 22(1),
2012, pp. 61–71.
[644] Emiliani, V., E. Entcheva, R. Hedrich, et al.,
“Optogenetics for light control of biological
systems”, Nat Rev Methods Primers 2(1),
2022, pp. 1–25.
[645] Churchland, M.M., J.P. Cunningham, M.T. Kaufman, et al.,
“Neural population dynamics during reaching”,
Nature 487(7405), 2012, pp. 51–56.
[646] Saxena, S., and J.P. Cunningham, “Towards the neural
population doctrine”, Curr. Opin. Neurobiol.
55, 2019, pp. 103–111.
[647] Ebitz, R.B., and B.Y. Hayden, “The population doctrine
in cognitive neuroscience”, Neuron
109(19), 2021, pp. 3055–3068.
[648] Gallego, J.A., M.G. Perich, L.E. Miller, and S.A. Solla,
“Neural manifolds for the control of movement”,
Neuron 94(5), 2017, pp. 978–984.
[649] Chung, S., and L.F. Abbott, “Neural population
geometry: An approach for understanding biological and artificial
neural networks”, Curr. Opin. Neurobiol.
70, 2021, pp. 137–144.
[650] Norman, K.A., S.M. Polyn, G.J. Detre, and J.V. Haxby,
“Beyond mind-reading: Multi-voxel pattern analysis of fMRI data”, Trends Cogn.
Sci. 10(9), 2006, pp. 424–430.
[651] Kriegeskorte, N., and J. Diedrichsen, “Inferring
brain-computational mechanisms with models of activity
measurements”, Philos. Trans. R. Soc. Lond. B Biol.
Sci. 371(1705), 2016.
[652] Bell, A.J., and T. Sejnowski, “A non-linear
information maximisation algorithm that performs blind
separation”, Adv. Neural Inf. Process. Syst.,
1994, pp. 467–474.
[653] Lee, D.D., and H.S. Seung, “Learning the parts of
objects by non-negative matrix factorization”,
Nature 401(6755), 1999, pp. 788–791.
[654] Williams, A.H., T.H. Kim, F. Wang, et al.,
“Unsupervised discovery of demixed, low-dimensional neural
dynamics across multiple timescales through tensor component
analysis”, Neuron 98(6), 2018, pp.
1099–1115.e8.
[655] Pellegrino, A., H. Stein, and N.A. Cayco-Gajic,
“Dimensionality reduction beyond neural subspaces with slice
tensor component analysis”, Nat. Neurosci.
27(6), 2024, pp. 1199–1210.
[656] Haxby, J.V., “Multivariate pattern analysis of fMRI: The early beginnings”,
Neuroimage 62(2), 2012, pp. 852–855.
[657] Naselaris, T., K.N. Kay, S. Nishimoto, and J.L. Gallant,
“Encoding and decoding in fMRI”, Neuroimage
56(2), 2011, pp. 400–410.
[658] Wang, H.-T., J. Smallwood, J. Mourao-Miranda, et al.,
“Finding the needle in a high-dimensional haystack:
Canonical correlation analysis for neuroscientists”,
Neuroimage 216, 2020, pp. 116745.
[659] Sussillo, D., “Neural circuits as computational
dynamical systems”, Curr. Opin. Neurobiol.
25, 2014, pp. 156–163.
[660] Strogatz, S., M. Friedman, A.J. Mallinckrodt, and S. McKay,
“Nonlinear dynamics and chaos: With applications to physics,
biology, chemistry, and engineering”, Comput. Phys.
Commun. 8(5), 1994, pp. 532–532.
[661] Khosla, M., A.H. Williams, J. McDermott, and N. Kanwisher,
“Privileged representational axes in biological and
artificial neural networks”, 2024.
[662] Prince, J.S., C. Conwell, G.A. Alvarez, and T. Konkle,
“A case for sparse positive alignment of neural
systems”, (2024).
[663] Sporns, O., G. Tononi, and R. Kötter, “The human
connectome: A structural description of the human brain”,
PLoS Comput. Biol. 1(4), 2005, pp. e42.
[664] Seung, S., Connectome: How the brain’s wiring makes us
who we are, Houghton Mifflin Harcourt, 2012.
[665] Bassett, D.S., and O. Sporns, “Network
neuroscience”, Nat. Neurosci. 20(3),
2017, pp. 353–364.
[666] Barabási, D.L., G. Bianconi, E. Bullmore, et al.,
“Neuroscience needs network science”, 2023.
[667] Hulse, B.K., H. Haberkern, R. Franconville, et al., “A
connectome of the drosophila central complex reveals network
motifs suitable for flexible navigation and context-dependent
action selection”, Elife 10, 2021, pp.
e66039.
[668] Shinomiya, K., A. Nern, I.A. Meinertzhagen, S.M. Plaza, and
M.B. Reiser, “Neuronal circuits integrating visual motion
information in drosophila melanogaster”, Curr.
Biol. 32(16), 2022, pp. 3529–3544.e2.
[669] Cammarata, N., G. Goh, S. Carter, C. Voss, L. Schubert, and
C. Olah, “Curve circuits”, Distill, 2021.
[670] Zeiler, M.D., and R. Fergus, “Visualizing and
understanding convolutional networks”, arXiv
[cs.CV], 2013.
[671] Cammarata, N., S. Carter, G. Goh, C. Olah, M. Petrov, and L.
Schubert, “Thread: circuits”, Distill
5(3), 2020, pp. e24.
[672] Wang, K., A. Variengien, A. Conmy, B. Shlegeris, and J.
Steinhardt, “Interpretability in the wild: A circuit for
indirect object identification in GPT-2
small”, arXiv [cs.LG], 2022.
[673] Heimersheim, S., and N. Nanda, “How to use and
interpret activation patching”, arXiv [cs.LG],
2024.
[674] Templeton, A., T. Conerly, J. Marcus, et al., “Scaling
monosemanticity: Extracting interpretable features from claude 3
sonnet”, Transformer Circuits Thread, 2024.
[675] Mueller, A., J. Brinkmann, M. Li, et al., “The quest
for the right mediator: A history, survey, and theoretical
grounding of causal interpretability”, arXiv
[cs.LG], 2024.
[676] Cunningham, H., A. Ewart, L. Riggs, R. Huben, and L.
Sharkey, “Sparse autoencoders find highly interpretable
features in language models”, arXiv [cs.LG], 2023.
[677] Gao, L., T.D. la Tour, H. Tillman, et al., “Scaling
and evaluating sparse autoencoders”, arXiv
[cs.LG], 2024.
[678] Alain, G., and Y. Bengio, “Understanding intermediate
layers using linear classifier probes”, arXiv
[stat.ML], 2016.
[679] Rumelhart, D.E., J.L. Mcclelland, and P.R. Group,
Parallel distributed processing, volume 1: Explorations in the
microstructure of cognition: foundations, Bradford Books,
Cambridge, Mass, 1987.
[680] Hinton, g.E., S. Osindero, and Y. Teh, “A fast
learning algorithm for deep belief nets”, Neural
Comput. 18(7), 2006, pp. 1527–1554.
[681] Lee, H., R. Grosse, R. Ranganath, and A.Y. Ng,
“Convolutional deep belief networks for scalable
unsupervised learning of hierarchical representations”,
Proceedings of the 26th international conference on machine
learning, (2009), 609–616.
[682] Barredo Arrieta, A., N. Díaz-Rodríguez, J. Del Ser, et al.,
“Explainable artificial intelligence (XAI):
Concepts, taxonomies, opportunities and challenges toward
responsible AI”, Inf. Fusion
58, 2020, pp. 82–115.
[683] Simonyan, K., A. Vedaldi, and A. Zisserman, “Deep
inside convolutional networks: Visualising image classification
models and saliency maps”, https://openreview.net ›
forumhttps://openreview.net › forum, 2013.
[684] Olah, C., A. Satyanarayan, I. Johnson, et al., “The
building blocks of interpretability”, Distill
3(3), 2018.
[685] Zimmermann, R.S., J. Borowski, R. Geirhos, M. Bethge, T.S.A.
Wallis, and W. Brendel, “How well do feature visualizations
support causal understanding of CNN
activations?”, Proceedings of the 35th international
conference on neural information processing systems, Curran
Associates Inc. (2024), 11730–11744.
[686] Freeman, J., C.M. Ziemba, D.J. Heeger, E.P. Simoncelli, and
J.A. Movshon, “A functional and perceptual signature of the
second visual area in primates”, Nat. Neurosci.
16(7), 2013, pp. 974–981.
[687] Olsson, C., N. Elhage, N. Nanda, et al., “In-context
learning and induction heads”, arXiv [cs.LG],
2022.
[688] Geva, M., J. Bastings, K. Filippova, and A. Globerson,
“Dissecting recall of factual associations in
auto-regressive language models”, arXiv [cs.CL],
2023.
[689] Nanda, N., L. Chan, T. Lieberum, J. Smith, and J.
Steinhardt, “Progress measures for grokking via mechanistic
interpretability”, arXiv [cs.LG], 2023.
[690] Quirke, P., C. Neo, and F. Barez, “Increasing trust in
language models through the reuse of verified circuits”,
arXiv [cs.LG], 2024.
[691] Syed, A., C. Rager, and A. Conmy, “Attribution
patching outperforms automated circuit discovery”,
arXiv [cs.LG], 2023.
[692] Conmy, A., A. Mavor-Parker, A. Lynch, S. Heimersheim, and A.
Garriga-Alonso, “Towards automated circuit discovery for
mechanistic interpretability”, Adv. Neural Inf.
Process. Syst. 36, 2023, pp. 16318–16352.
[693] Weiss, G., Y. Goldberg, and E. Yahav, “Thinking like
transformers”, arXiv [cs.LG], 2021.
[694] Zhou, H., A. Bradley, E. Littwin, et al., “What
algorithms can transformers learn? A study in length
generalization”, 2023.
[695] Lindner, D., J. Kramar, S. Farquhar, M. Rahtz, T. McGrath,
and V. Mikulik, “Tracr: Compiled transformers as a
laboratory for interpretability”, arXiv, 2023.
[696] Kohonen, T., P. Lehtiö, J. Rovamo, J. Hyvärinen, K. Bry, and
L. Vainio, “A principle of neural associative
memory”, Neuroscience 2(6), 1977, pp.
1065–1076.
[697] Hopfield, J.J., “Neural networks and physical systems
with emergent collective computational abilities”,
Proc. Natl. Acad. Sci. U. S. A. 79(8), 1982, pp.
2554–2558.
[698] Hinton, G.E., “Learning distributed representations of
concepts”, In R.G.M. Morris, ed., Parallel distributed
processing: Implications for psychology and neurobiology (pp.
Clarendon Press/Oxford University Press, x, New York, NY, US,
1989, 46–61.
[699] Thorpe, S., “Local vs. Distributed coding”,
Intellectica 8(2), 1989, pp. 3–40.
[700] Rigotti, M., O. Barak, M.R. Warden, et al., “The
importance of mixed selectivity in complex cognitive
tasks”, Nature 497(7451), 2013, pp.
585–590.
[701] Bricken, T., A. Templeton, J. Batson, et al., “Towards
monosemanticity: Decomposing language models with dictionary
learning”, Transformer Circuits Thread, 2023.
[702] McDougall, C.S., A. Conmy, C. Rushing, T. McGrath, and N.
Nanda, “Copy suppression: Comprehensively understanding an
attention head”, https://openreview.net ›
forumhttps://openreview.net › forum, 2023.
[703] Rajamanoharan, S., T. Lieberum, N. Sonnerat, et al.,
“Jumping ahead: Improving reconstruction fidelity with
JumpReLU sparse autoencoders”, arXiv
[cs.LG], 2024.
[704] Rajamanoharan, S., A. Conmy, L. Smith, et al.,
“Improving dictionary learning with gated sparse
autoencoders”, arXiv [cs.LG], 2024.
[705] Lieberum, T., S. Rajamanoharan, A. Conmy, et al.,
“Gemma scope: Open sparse autoencoders everywhere all at
once on gemma 2”, arXiv [cs.LG], 2024.
[706] Marks, S., C. Rager, E.J. Michaud, Y. Belinkov, D. Bau, and
A. Mueller, “Sparse feature circuits: Discovering and
editing interpretable causal graphs in language models”,
arXiv [cs.LG], 2024.
[707] Marks, S., and M. Tegmark, “The geometry of truth:
Emergent linear structure in large language model representations
of true/false datasets”, arXiv [cs.AI], 2023.
[708] Sharma, A.S., D. Atkinson, and D. Bau, “Locating and
editing factual associations in mamba”, arXiv
[cs.CL], 2024.
[709] Wang, J., X. Ge, W. Shu, et al., “Towards
universality: Studying mechanistic similarity across language
model architectures”, arXiv [cs.CL], 2024.
[710] Liu, Z., E. Gan, and M. Tegmark, “Seeing is believing:
Brain-inspired modular training for mechanistic
interpretability”, Entropy (Basel) 26(1),
2023.
[711] Jarvis, D., R. Klein, B. Rosman, and A.M. Saxe, “On
the specialization of neural modules”, arXiv
[cs.LG], 2024.
[712] Clune, J., J.-B. Mouret, and H. Lipson, “The
evolutionary origins of modularity”, Proc. Biol.
Sci. 280(1755), 2013, pp. 20122863.
[713] Margalit, E., H. Lee, D. Finzi, J.J. DiCarlo, K.
Grill-Spector, and D.L.K. Yamins, “A unifying framework for
functional organization in early and higher ventral visual
cortex”, Neuron 112(14), 2024, pp.
2435–2451.e7.
[714] Kouh, M., and T. Poggio, “A canonical neural circuit
for cortical nonlinear operations”, Neural Comput.
20(6), 2008, pp. 1427–1451.
[715] Liu, Z., Y. Wang, S. Vaidya, et al.,
“KAN: Kolmogorov-arnold networks”, 2024.
[716] Steinmetz, N.A., C. Aydin, A. Lebedeva, et al.,
“Neuropixels 2.0: A miniaturized high-density probe for
stable, long-term brain recordings”, Science
372(6539), 2021, pp. eabf4588.
[717] Meng, Y., K. Hynynen, and N. Lipsman, “Applications of
focused ultrasound in the brain: From thermoablation to drug
delivery”, Nat. Rev. Neurol. 17, 2020,
pp. 7–22.
[718] Sevilla, J., L. Heim, A. Ho, T. Besiroglu, M. Hobbhahn, and
P. Villalobos, “Compute trends across three eras of machine
learning”, arXiv [cs.LG], 2022.
[719] Markiewicz, C.J., K.J. Gorgolewski, F. Feingold, et al.,
“The
OpenNeuro resource for sharing of neuroscience
data”, eLife 10, 2021, pp. e71774.
[720] Marblestone, A., A. Gamick, T. Kalil, C. Martin, M.
Cvitkovic, and S.G. Rodriques, “Unblock research bottlenecks
with non-profit start-ups”, Nature
601(7892), 2022, pp. 188–190.
[721] Greydanus, S., and D. Kobak, “Scaling down deep
learning with MNIST-1D”,
arXiv [cs.LG], 2020.
[722] Wang, G., Y. Sun, S. Cheng, and S. Song, “Evolving
connectivity for recurrent spiking neural networks”,
Neural information processing systems, (2023).
[723] Abril-Pla, O., V. Andreani, C. Carroll, et al.,
“PyMC: A modern, and comprehensive
probabilistic programming framework in python”, PeerJ
Comput. Sci. 9, 2023, pp. e1516.
[724] Stringer, C., M. Pachitariu, N. Steinmetz, C.B. Reddy, M.
Carandini, and K.D. Harris, “Spontaneous behaviors drive
multidimensional, brainwide activity”, Science
364(6437), 2019, pp. 255.
[725] Halchenko, Y., J.T.W. II, H. Christian, et al.,
“Dandi/dandi-cli: 0.64.0”, 2024. https://zenodo.org/records/14171788
[726] Rübel, O., A. Tritt, R. Ly, et al., “The
Neurodata Without Borders
ecosystem for neurophysiological data science”,
eLife 11, 2022, pp. e78362.
[727] Gorgolewski, K.J., T. Auer, V.D. Calhoun, et al., “The brain imaging
data structure, a format for organizing and describing outputs of
neuroimaging experiments”, Scientific Data
3(1), 2016, pp. 160044.
[728] Miller, K.L., F. Alfaro-Almagro, N.K. Bangerter, et al.,
“Multimodal
population brain imaging in the UK
Biobank prospective epidemiological
study”, Nature Neuroscience 19(11),
2016, pp. 1523–1536.
[729] Kalcher, K., W. Huf, R.N. Boubela, et al., “Fully exploratory
network independent component analysis of the 1000 functional
connectomes database”, Frontiers in Human
Neuroscience 6, 2012.
[730] Van Essen, D.C., K. Ugurbil, E. Auerbach, et al., “The
Human Connectome Project:
A data acquisition perspective”,
NeuroImage 62(4), 2012, pp. 2222–2231.
[731] Casey, B.J., T. Cannonier, M.I. Conley, et al., “The
Adolescent Brain Cognitive
Development (ABCD) study:
Imaging acquisition across 21 sites”,
Developmental Cognitive Neuroscience 32, 2018,
pp. 43–54.
[732] Alexander, L.M., J. Escalera, L. Ai, et al., “An open resource for
transdiagnostic research in pediatric mental health and learning
disorders”, Scientific Data 4(1),
2017, pp. 170181.
[733] Boyle, J., B. Pinsard, V. Borghesani, F. Paugam, E. DuPre,
and P. Bellec, “The
Courtois NeuroMod project: Quality
assessment of the initial data release (2020)”,
2023 Conference on Cognitive
Computational Neuroscience,
Cognitive Computational Neuroscience (2023).
[734] Seeliger, K., R.P. Sommers, U. Güçlü, S.E. Bosch, and M.A.J.
Van Gerven, “A large single-participant fMRI dataset for probing brain responses to
naturalistic stimuli in space and time”, 2019. http://biorxiv.org/lookup/doi/10.1101/687681
[735] Siegel, J.S., S. Subramanian, D. Perry, et al., “Psilocybin
desynchronizes the human brain”, Nature
632(8023), 2024, pp. 131–138.