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.
翻译:我们简要回顾了生物学习的共同假设和实验神经科学的研究结果,并将这些假设与经常性神经网络中的梯度学习效率作了对比,本审查讨论的主要问题包括:合成塑料、神经电路、理论-实验分化和客观功能。 我们最后建议理论和实验神经科学家在设计有助于澄清这些问题的新研究时,同时提出理论和实验性神经科学家的建议。