Hostname: page-component-f554764f5-c4bhq Total loading time: 0 Render date: 2025-04-22T10:32:31.466Z Has data issue: false hasContentIssue false
  • English
  • Français

The hard problem of meta-learning is what-to-learn

Published online by Cambridge University Press:  23 September 2024

Yosef Prat Open the ORCID record for Yosef Prat [Opens in a new window]  and
Ehud Lamm Open the ORCID record for Ehud Lamm [Opens in a new window]
Yosef Prat*
Affiliation:
The Cohn Institute for History and Philosophy of Science and Ideas, Tel Aviv University, Tel Aviv, Israel [email protected] [email protected] https://www.ehudlamm.com
Ehud Lamm
Affiliation:
The Cohn Institute for History and Philosophy of Science and Ideas, Tel Aviv University, Tel Aviv, Israel [email protected] [email protected] https://www.ehudlamm.com
*
*Corresponding author.
Get access Rights & Permissions [Opens in a new window]

Abstract

Binz et al. highlight the potential of meta-learning to greatly enhance the flexibility of AI algorithms, as well as to approximate human behavior more accurately than traditional learning methods. We wish to emphasize a basic problem that lies underneath these two objectives, and in turn suggest another perspective of the required notion of “meta” in meta-learning: knowing what to learn.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 47 , 2024 , e161
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

Ben-Oren, Y., Truskanov, N., & Lotem, A. (2022). House sparrows use learned information selectively based on whether reward is hidden or visible. Animal Cognition, 25(6), 1545–1555. https://doi.org/10.1007/s10071-022-01637-1CrossRefGoogle ScholarPubMed
Dunlap, A. S., & Stephens, D. W. (2016). Reliability, uncertainty, and costs in the evolution of animal learning. Current Opinion in Behavioral Sciences, 12, 73–79. https://doi.org/https://doi.org/10.1016/j.cobeha.2016.09.010CrossRefGoogle Scholar
Ellefsen, K. O., Mouret, J.-B., & Clune, J. (2015). Neural modularity helps organisms evolve to learn new skills without forgetting old skills. PLoS Computational Biology, 11(4), e1004128. https://doi.org/doi.org/10.1371/journal.pcbi.1004128CrossRefGoogle ScholarPubMed
Fedorenko, E., & Blank, I. A. (2020). Broca's area is not a natural kind. Trends in Cognitive Sciences, 24(4), 270–284. https://doi.org/10.1016/j.tics.2020.01.001CrossRefGoogle Scholar
Heyes, C. (2018). Cognitive gadgets: The cultural evolution of thinking. Harvard University Press. https://doi.org/10.2307/j.ctv24trbqxGoogle Scholar
Houston, A. I., McNamara, J. M., & Steer, M. D. (2007). Do we expect natural selection to produce rational behaviour? Philosophical Transactions of the Royal Society B: Biological Sciences, 362(1485), 1531–1543. https://doi.org/10.1098/rstb.2007.2051CrossRefGoogle ScholarPubMed
Kacelnik, A. (2006). Meanings of rationality. In Hurley, S. & Nudds, M. (Eds.), Rational animals? (pp. 87–106). Oxford University Press. https://doi.org/10.1093/acprof:oso/9780198528272.003.0002CrossRefGoogle Scholar
Laland, K. N. (2004). Social learning strategies. Animal Learning & Behavior, 32(1), 4–14. https://doi.org/10.3758/BF03196002CrossRefGoogle ScholarPubMed
Lotem, A., & Halpern, J. Y. (2012). Coevolution of learning and data-acquisition mechanisms: A model for cognitive evolution. Philosophical Transactions of the Royal Society B: Biological Sciences, 367(1603), 2686–2694. https://doi.org/10.1098/rstb.2012.0213CrossRefGoogle Scholar
Niv, Y. (2019). Learning task-state representations. Nature Neuroscience, 22(10), 1544–1553. https://doi.org/10.1038/s41593-019-0470-8CrossRefGoogle ScholarPubMed
Niv, Y., Daniel, R., Geana, A., Gershman, S. J., Leong, Y. C., Radulescu, A., & Wilson, R. C. (2015). Reinforcement learning in multidimensional environments relies on attention mechanisms. The Journal of Neuroscience, 35(21), 8145–8157. https://doi.org/10.1523/JNEUROSCI.2978-14.2015CrossRefGoogle ScholarPubMed
Prat, Y., Bshary, R., & Lotem, A. (2022). Modelling how cleaner fish approach an ephemeral reward task demonstrates a role for ecologically tuned chunking in the evolution of advanced cognition. PLoS Biology, 20(1), e3001519. https://doi.org/10.1371/journal.pbio.3001519CrossRefGoogle ScholarPubMed
Roli, A., Jaeger, J., & Kauffman, S. A. (2022). How organisms come to know the world: Fundamental limits on artificial general intelligence. Frontiers in Ecology and Evolution, 9, 806283. https://doi.org/10.3389/fevo.2021.806283CrossRefGoogle Scholar
Sporns, O., & Betzel, R. F. (2016). Modular brain networks. Annual Review of Psychology, 67(1), 613–640. https://doi.org/10.1146/annurev-psych-122414-033634CrossRefGoogle ScholarPubMed
Tversky, A., & Kahneman, D. (1981). The framing of decisions and the psychology of choice. Science, 211(4481), 453–458. https://doi.org/10.1126/science.7455683CrossRefGoogle ScholarPubMed
Warrant, E. J. (2016). Sensory matched filters. Current Biology, 26(20), R976–R980. https://doi.org/https://doi.org/10.1016/j.cub.2016.05.042CrossRefGoogle ScholarPubMed