论文标题
预测性编码，变异自动编码器和生物连接
Predictive Coding, Variational Autoencoders, and Biological Connections
论文作者
论文摘要
本文回顾了从理论神经科学和变异自动编码器的预测编码，从机器学习，确定两个领域的共同起源和数学框架。由于每个领域在各自的领域都很突出，因此更牢固地连接这些领域可能会在神经科学和机器学习之间对话中有用。在回顾了每个区域后，我们讨论了这种视角所隐含的两个可能的对应关系：皮质锥体树突类似于（非线性）深网和横向抑制作用，类似于归一化流。这些连接可能为每个领域的进一步研究提供新的方向。
This paper reviews predictive coding, from theoretical neuroscience, and variational autoencoders, from machine learning, identifying the common origin and mathematical framework underlying both areas. As each area is prominent within its respective field, more firmly connecting these areas could prove useful in the dialogue between neuroscience and machine learning. After reviewing each area, we discuss two possible correspondences implied by this perspective: cortical pyramidal dendrites as analogous to (non-linear) deep networks and lateral inhibition as analogous to normalizing flows. These connections may provide new directions for further investigations in each field.
