Compositional pretraining improves computational efficiency and matches animal behaviour on complex tasks
Yang, Gr & Wang, X.-J. Artificial nerve networks for neurologists: primer. Nerve cells 1071048-1070 (2020).
Krueger, Ka & Dayan, P. Flexible Forming: How to learn in small steps. perception 110380-394 (2009).
Narvekar, S. Et al. Learning the curricula for reinforcement learning fields: frame and survey. C. Mach. Learn. Accuracy. 21181 (2020).
Bengio, Y., Louradour, J., Colobert, R. & Weston, J. Learning Curriculum. in Brook. 26 annually. Methodology Conference 41-48 (Computing Machines Association, 2009).
Finn, C., Abbeel, P. & Levine, S. Model-Agnostic Meta Leachning For Fast Texpative of Deep Networks. in int. Methodology Conference1126-1135 (PMLR, 2017).
Thrun, S. & Pratt, L. In Learning learning (Eds Thrun, S. & Pratt, L.) 3-17 (Springer, 1998).
Harlo, HF Forming Learning Communities. Psychol. pastor 5651-65 (1949).
Skinner, b. Sci. I am. 18526-29 (1951).
SAVIN, C. & Triesch, J. The appearance of task -dependent representations in the working memory circles. before. account. Neurosci. 857 (2014).
MCANDREW, R. & Helms Tillery, Si Laboratory Cripates: their lives in and after the search. Temperature https://doi.org/10.1080/23328940.2016.1229161 (2016).
Chowdhury, SA & Deangelis, GC Training on Displacing the fine changes the causal contribution of the MT to perceive depth. Nerve cells 60367-377 (2008).
ARLT, C. Et al. The cognitive experience changes the cortical participation in the movement directed to the goals. Elife 11E76051 (2022).
Wang, JX Meta Learning in natural and artificial intelligence. Curr. Opinion. behavior. Sci. 3890-95 (2021).
Vanderschuren, LJ, Achterberg, EM & Trezza, V. Neuroscience for social play and their rewarding value in mice. Neurosci. biobehav. pastor 7086-105 (2016).
Vanderschuren, LJ & Trezza, V. What we taught the laboratory mice about social playing behavior: a role in behavioral development and nervous mechanisms. in Childhood biology (Eds Andersen, SL & Pine, DS) 189-212 (Springer, 2014).
Baarendse, PJ, Limpens, JH & Vanderschuren, LJ disrupts social development enhances cocaine in mice. Psychology 2311695-1704 (2014).
Einon, DF & Morgan, M. A critical period of social isolation in mice. Dave. Psychobiol. J. INT. Suk. Dave. Psychobiol. 10123-132 (1977).
Zador, I am a criticism of pure learning and what artificial nerve networks can learn from animal brains. Nat. communication. 103770 (2019).
Maah, A., Schiereck, SS, Bossio, V. & CONSTANTINOPLE, supported by distinctive value CM accounts, fast serial decisions. Nat. communication. 147573 (2023).
Schiereck, SS et al. Neurological dynamics in the tropical front shell reveals cognitive strategies. Preprint in BIORXIV https://doi.org/10.1101/2024.10.29.620879 (2024).
Constantino, SM & DAW, ND Learn the time cost of time on the correction correction mission. The gear. It affects. behavior. Neurosci. 15837-853 (2015).
Charnov, optimal feed feed, marginal value theory. theory. Peoples. Biol. 9129-136 (1976).
McNamara, JM & Houston, AI Feed and Optimal Learning. J. Theor. Biol. 117231-249 (1985).
Wang, JX et al. Gibbian lobe crust as a metapical reinforcement learning system. Nat. Neurosci. 21860-868 (2018).
Wilson, RC, Takahashi, YK, Schoenbauum, G. & NIV, Y. Orbitofrontal Cortex as a cognitive map of the mission space. Nerve cells 81267-279 (2014).
Schuck, NW, CAI, MB, Wilson, RC & NIV, Y. Human Human orbit Calcular Cortex are a cognitive map of the status space. Nerve cells 911402-1412 (2016).
Bartolo, R. & Averbeck, BB inference as a basic behavior. Curr. Opinion. behavior. Sci. 388-13 (2021).
Averbeck, B. & O’Doherty, JP learning in the front circles. Nerve pharmaceutical 47147-162 (2022).
MIYASHITA, Y. & Chang, HS Neuronal Link to the short -term pictorial memory in the main cortical cortical dandruff. nature 33168-70 (1988).
Dubreuil, A., Valente, A., Beiran, M., Mastroguseppe, F. & Ostojic, S. The role of the population structure in accounts through nerve dynamics. Nat. Neurosci. 25783-794 (2022).
Khuna, m. Nat. Neurosci priest. 23744-766 (2022).
Marschalle, O. & SAVIN, C. Investigation of learning through the lens of changes in the dynamics of the circle. Preprint in BIORXIV https://doi.org/10.1101/2023.09.13.557585 (2023).
Sussillo, D. & Barak, O. Opening the Black Box: Low DyD dynamics in frequent high -dimensional nerve networks. Nervous computing. 25626-649 (2013).
Elman, JL Learning and Development in Nervous Networks: The importance of small start. perception 4871-99 (1993).
Kepple, D., Engelken, R. & Rajan, K. Learning Curiculum Corniculum as a tool to detect the principles of learning in the brain. in int. Learning conference representations (2022).
Silver, D. et al. Mastering the game by going with deep nerve networks and searching for trees. nature 529484-489 (2016).
Jensen, KT, Hennequin, G. & Mattar, MG Frequent Planning Model Explaining Human Restart and Human Behavior. Nat. Neurosci. 271340-1348 (2024).
Braun, Da, Mehring, C. & Wolpet, DM Brucking Learning in Action. behavior. The accuracy of the brain. 206157-165 (2010).
Makino, H. Representation of the arithmetic value of the formation of hierarchical behavior. Nat. Neurosci. 26140-149 (2023).
Driscoll, LN, Shenoy, K. & Sussillo, D. Complasse Multitsible Multitsbas are used in repeated networks of common dynamic motifs. Nat. Neurosci. 271349-1363 (2024).
Gupta, D., DePasquale, B., Kopec, CD & Brody, CD’s experiences in the accumulation of evidence can lead to clear lapses in decision -making. Nat. communication. 15662 (2024).
Richards, Ba and others. A deep learning frame for neuroscience. Nat. Neurosci. 221761-1770 (2019).
MA, WJ & PEERS, B. The nerve network enters into the laboratory: Towards the use of deep nets as models for human behavior. Preprint at https://arxiv.org/abs/2005.02181 (2020).
Goldman, MS Memory without comments in a nervous network. Nerve cells 61621-634 (2009).
Maah, A., Schiereck, S., Bossio, V. & Constantinople, C. Distinguished Value Accounts supports fast serial decisions (version V1). Zenudo https://doi.org/10.5281/zenodo.10031483 (2023).
HOCKER, D., Constantinople, CM & Savin, C. Simple mathematical tasks capture inductive biases of animals in network models (version V1). Zenudo https://doi.org/10.5281/zenodo.14907819 (2025).
HOCKER, D., Constantinople, CM & Savin, C. Savin-Lab-Code/Kind_cl: Nature Machine Intelligence Code (V1.0.0). Zenudo https://doi.org/10.5281/zenodo.14907734 (2025).
HOCKER, D., Constantinople, CM & Savin, C. Pretroing Copporcelration improves mathematical efficiency and coincides with animal behavior in complex tasks. Ocean capsule code https://doi.org/10.24433/co.33440797.v1 (2025).
Arnold, TB & Emerson, JW Nonparametric Good -f Forts for separate empty distributions. R J. 334-39 (2011).
Don’t miss more hot News like this! Click here to discover the latest in AI news!
2025-05-19 00:00:00
