NCAIMay 12, 2021

Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece

arXiv:2105.05382v24 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental perspective piece aimed at theoretical and experimental neuroscientists to bridge gaps in understanding biological learning mechanisms.

The paper reviews assumptions about biological learning in recurrent neural networks, contrasting experimental neuroscience findings with gradient-based learning efficiency, and provides recommendations for future studies.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes