Hostname: page-component-89b8bd64d-r6c6k Total loading time: 0 Render date: 2026-05-14T03:40:46.421Z Has data issue: false hasContentIssue false
  • English
  • Français

The meta-learning toolkit needs stronger constraints

Published online by Cambridge University Press:  23 September 2024

Erin Grant Open the ORCID record for Erin Grant [Opens in a new window]
Erin Grant*
Affiliation:
UCL Gatsby Unit, Sainsbury Wellcome Centre, University College London, London, UK erin.grant@ucl.ac.uk https://eringrant.github.io/
*
*Corresponding author.
Get access Rights & Permissions [Opens in a new window]

Abstract

The implementation of meta-learning targeted by Binz et al. inherits benefits and drawbacks from its nature as a connectionist model. Drawing from historical debates around bottom-up and top-down approaches to modeling in cognitive science, we should continue to bridge levels of analysis by constraining meta-learning and meta-learned models with complementary evidence from across the cognitive and computational sciences.

Information

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 47 , 2024 , e152
Check for updates
Copyright
Copyright © The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Dominé, C. C., Braun, L., Fitzgerald, J. E., & Saxe, A. M. (2023). Exact learning dynamics of deep linear networks with prior knowledge. Journal of Statistical Mechanics: Theory and Experiment, 2023(11), 114004. https://doi.org/10.1088/1742-5468/ad01b8CrossRefGoogle Scholar
Griffiths, T. L., Vul, E., & Sanborn, A. N. (2012). Bridging levels of analysis for probabilistic models of cognition. Current Directions in Psychological Science, 21(4), 263–268. https://doi.org/10.1177/0963721412447619CrossRefGoogle Scholar
Lindsey, J. W., & Lippl, S. (2023). Implicit regularization of multi-task learning and finetuning in overparameterized neural networks. arXiv preprint arXiv:2310.02396. https://doi.org/10.48550/arXiv.2310.02396CrossRefGoogle Scholar
McCoy, R. T., Grant, E., Smolensky, P., Griffiths, T. L., & Linzen, T. (2020). Universal linguistic inductive biases via meta-learning. In Proceedings of the Annual Meeting of the Cognitive Science Society. https://doi.org/10.48550/arXiv.2006.16324CrossRefGoogle Scholar
Ortega, P. A., Wang, J. X., Rowland, M., Genewein, T., Kurth-Nelson, Z., Pascanu, R., … Legg, S. (2019). Meta-learning of sequential strategies. arXiv preprint arXiv:1905.03030. https://doi.org/10.48550/arXiv.1905.03030CrossRefGoogle Scholar
Rogers, T. T., & McClelland, J. L. (2008). A simple model from a powerful framework that spans levels of analysis. Behavioral and Brain Sciences, 31(6), 729–749. doi:10.1017/S0140525X08006067CrossRefGoogle Scholar
Smolensky, P. (1988). On the proper treatment of connectionism. Behavioral and Brain Sciences, 11(1), 1–23. https://doi.org/10.1017/S0140525X00052432CrossRefGoogle Scholar
Wang, J. X., Kurth-Nelson, Z., Kumaran, D., Tirumala, D., Soyer, H., Leibo, J. Z., … Botvinick, M. (2018). Prefrontal cortex as a meta-reinforcement learning system. Nature Neuroscience 21, 860–868. https://doi.org/10.1038/s41593-018-0147-8CrossRefGoogle ScholarPubMed