CCN GAC Workshop: Issues with learning in biological recurrent neural
networks
networks
File(s)
Working paper
Author(s)
Type
Working Paper
Abstract
This perspective piece came about through the Generative Adversarial
Collaboration (GAC) series of workshops organized by the Computational
Cognitive Neuroscience (CCN) conference in 2020. We brought together a number
of experts from the field of theoretical neuroscience to debate emerging issues
in our understanding of how learning is implemented in biological recurrent
neural networks. Here, we will give a brief review of the common assumptions
about biological learning and the corresponding findings from experimental
neuroscience and contrast them with the efficiency of gradient-based learning
in recurrent neural networks commonly used in artificial intelligence. We will
then outline the key issues discussed in the workshop: synaptic plasticity,
neural circuits, theory-experiment divide, and objective functions. Finally, we
conclude with recommendations for both theoretical and experimental
neuroscientists when designing new studies that could help to bring clarity to
these issues.
Collaboration (GAC) series of workshops organized by the Computational
Cognitive Neuroscience (CCN) conference in 2020. We brought together a number
of experts from the field of theoretical neuroscience to debate emerging issues
in our understanding of how learning is implemented in biological recurrent
neural networks. Here, we will give a brief review of the common assumptions
about biological learning and the corresponding findings from experimental
neuroscience and contrast them with the efficiency of gradient-based learning
in recurrent neural networks commonly used in artificial intelligence. We will
then outline the key issues discussed in the workshop: synaptic plasticity,
neural circuits, theory-experiment divide, and objective functions. Finally, we
conclude with recommendations for both theoretical and experimental
neuroscientists when designing new studies that could help to bring clarity to
these issues.
Date Issued
2021-05-12
Citation
2021
Copyright Statement
© 2021 The Author(s). This work is licensed under CC BY license.
License URL
Identifier
http://arxiv.org/abs/2105.05382v1
Subjects
q-bio.NC
q-bio.NC
cs.AI
Publication Status
Published