Hostname: page-component-669899f699-qzcqf Total loading time: 0 Render date: 2025-05-06T05:07:40.607Z Has data issue: false hasContentIssue false
  • English
  • Français

Linking meta-learning to meta-structure

Published online by Cambridge University Press:  23 September 2024

Malte Schilling Open the ORCID record for Malte Schilling [Opens in a new window] ,
Helge J. Ritter  and
Frank W. Ohl
Malte Schilling*
Affiliation:
Autonomous Intelligent Systems Group, Computer Science Department, University of Münster, Münster, Germany [email protected] https://www.uni-muenster.de/AISystems/
Helge J. Ritter
Affiliation:
Neuroinformatics Group Faculty of Technology/CITEC, Bielefeld University, Bielefeld, Germany [email protected] https://ni.www.techfak.uni-bielefeld.de/people/helge/
Frank W. Ohl
Affiliation:
Department of Systems Physiology of Learning, Leibniz Institute for Neurobiology, Magdeburg, Germany [email protected] Institute of Biology, Otto-von-Guericke University, Magdeburg, Germany https://www.ovgu.de/Ohl.html
*
*Corresponding author.
Get access Rights & Permissions [Opens in a new window]

Abstract

We propose that a principled understanding of meta-learning, as aimed for by the authors, benefits from linking the focus on learning with an equally strong focus on structure, which means to address the question: What are the meta-structures that can guide meta-learning?

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 47 , 2024 , e164
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

Dickinson, M. H., Farley, C. T., Full, R. J., Koehl, M., Kram, R., & Lehman, S. (2000). How animals move: An integrative view. Science 288(5463), 100–106. https://doi.org/10.1126/science.288.5463.100CrossRefGoogle ScholarPubMed
Happel, M. F., Niekisch, H., Castiblanco Rivera, L. L., Ohl, F. W., Deliano, M., & Frischknecht, R. (2014). Enhanced cognitive flexibility in reversal learning induced by removal of the extracellular matrix in auditory cortex. Proceedings of the National Academy of Sciences, 111(7), 2800–2805.CrossRefGoogle ScholarPubMed
Jarvers, C., Brosch, T., Brechmann, A., Woldeit, M. L., Schulz, A. L., Ohl, F. W., … Neumann, H. (2016). Reversal learning in humans and gerbils: Dynamic control network facilitates learning. Frontiers in Neuroscience, 10, 535.CrossRefGoogle ScholarPubMed
Merel, J., Botvinick, M., & Wayne, G. (2019). Hierarchical motor control in mammals and machines. Nature Communications, 10(1), 5489.CrossRefGoogle ScholarPubMed
Neftci, E. O., & Averbeck, B. B. (2019). Reinforcement learning in artificial and biological systems. Nature Machine Intelligence, 1(3), 133–143.CrossRefGoogle Scholar
Schilling, M., Hammer, B., Ohl, F. W., Ritter, H. J., & Wiskott, L. (2023). Modularity in nervous systems – a key to efficient adaptivity for deep reinforcement learning. Cognitive Computation, 1–16.Google Scholar
Schilling, M., Melnik, A., Ohl, F. W., Ritter, H. J., & Hammer, B. (2021). Decentralized control and local information for robust and adaptive decentralized deep reinforcement learning. Neural Networks, 144, 699–725.CrossRefGoogle ScholarPubMed