Back to Search
Start Over
Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
- Publication Year :
- 2021
-
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.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2105.05382
- Document Type :
- Working Paper