v1v2 (latest)
Current State and Future Directions for Learning in Biological Recurrent
Neural Networks: A Perspective Piece
Neurons, Behavior, Data analysis, and Theory (NBDT), 2021
- CLL
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.
View on arXivComments on this paper
