[论文解读] Predictive Coding: a Theoretical and Experimental Review

Beren Millidge, Anil K. Seth+1 more|arXiv (Cornell University)|Jul 27, 2021

Neural dynamics and brain function参考文献 164被引用 26

一句话总结

本文综述预测编码作为贝叶斯变分推断框架，评估其数学结构、神经实现，以及与机器学习和控制理论的联系。

ABSTRACT

Predictive coding offers a potentially unifying account of cortical function -- postulating that the core function of the brain is to minimize prediction errors with respect to a generative model of the world. The theory is closely related to the Bayesian brain framework and, over the last two decades, has gained substantial influence in the fields of theoretical and cognitive neuroscience. A large body of research has arisen based on both empirically testing improved and extended theoretical and mathematical models of predictive coding, as well as in evaluating their potential biological plausibility for implementation in the brain and the concrete neurophysiological and psychological predictions made by the theory. Despite this enduring popularity, however, no comprehensive review of predictive coding theory, and especially of recent developments in this field, exists. Here, we provide a comprehensive review both of the core mathematical structure and logic of predictive coding, thus complementing recent tutorials in the literature. We also review a wide range of classic and recent work within the framework, ranging from the neurobiologically realistic microcircuits that could implement predictive coding, to the close relationship between predictive coding and the widely-used backpropagation of error algorithm, as well as surveying the close relationships between predictive coding and modern machine learning techniques.

研究动机与目标

• 在概率（变分）框架内总结预测编码的核心数学结构和逻辑。
• 调查神经生物学的可行性及提出的皮层微回路实现。
• 回顾预测编码与机器学习方法的联系，包括反向传播和归一化流。
• 探索对动态、精度和行动/主动推理的扩展。

提出的方法

• 将预测编码框定为带高斯生成模型的变分推断。
• 从变分自由能推导预测编码更新规则。 定义预测误差及其在更新状态和参数中的作用。
• 讨论类似 EM 的交替优化，用于在后验同时学习生成模型。
• 将预测编码与经典算法（卡尔曼滤波、反向传播）以及主动推理联系起来。

实验结果

研究问题

• RQ1 如何将预测编码表述为近似贝叶斯/推理过程？
• RQ2 预测编码在整个层级中最小化预测误差的数学机制是什么？
• RQ3 如何在生物学上可行的神经微回路中实现预测编码？
• RQ4 预测编码与已建立的机器学习方法（如反向传播和归一化流）之间的关系是什么？
• RQ5 动态、精度和行动如何整合到预测编码框架中？（包括主动推理）

主要发现

• 预测编码可以被重新表述为最小化自由能界的变分推断。
• 该能量项简化为加权预测误差的和，连接感知与学习。
• 梯度下降更新为分层模型中的状态和参数学习提供了具体规则。
• 在某些假设下，该框架与卡尔曼滤波和反向传播等既有算法相接轨。
• 对动态、精度和行动的扩展将预测编码与主动推理和控制理论联系起来。