Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
Abstract
We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them with the efficiency of gradient-based learning in recurrent neural networks. The key issues discussed in this review include: synaptic plasticity, neural circuits, theory-experiment divide, and objective functions. We conclude with recommendations for both theoretical and experimental neuroscientists when designing new studies that could help bring clarity to these issues.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2021
- DOI:
- 10.48550/arXiv.2105.05382
- arXiv:
- arXiv:2105.05382
- Bibcode:
- 2021arXiv210505382P
- Keywords:
-
- Quantitative Biology - Neurons and Cognition;
- Computer Science - Artificial Intelligence