Recent years have witnessed a growing call for renewed emphasis on neuroscience-inspired approaches in artificial intelligence research, under the banner of $\textit{NeuroAI}$. This is exemplified by recent attention gained by predictive coding networks (PCNs) within machine learning (ML). PCNs are based on the neuroscientific framework of predictive coding (PC), which views the brain as a hierarchical Bayesian inference model that minimizes prediction errors from feedback connections. PCNs trained with inference learning (IL) have potential advantages to traditional feedforward neural networks (FNNs) trained with backpropagation. While historically more computationally intensive, recent improvements in IL have shown that it can be more efficient than backpropagation with sufficient parallelization, making PCNs promising alternatives for large-scale applications and neuromorphic hardware. Moreover, PCNs can be mathematically considered as a superset of traditional FNNs, which substantially extends the range of possible architectures for both supervised and unsupervised learning. In this work, we provide a comprehensive review as well as a formal specification of PCNs, in particular placing them in the context of modern ML methods, and positioning PC as a versatile and promising framework worthy of further study by the ML community.

翻译：近年来，人工智能研究领域日益强调神经科学启发的范式，这一趋势在 $\textit{NeuroAI}$ 的旗帜下愈发显著。机器学习（ML）领域对预测编码网络（PCNs）的关注正是这一趋势的体现。PCNs 基于神经科学中的预测编码（PC）框架，该框架将大脑视为一个分层贝叶斯推理模型，通过反馈连接最小化预测误差。采用推理学习（IL）训练的 PCNs 相较于基于反向传播训练的传统前馈神经网络（FNNs）具有潜在优势。尽管历史上其计算成本较高，但 IL 的最新改进表明，在充分并行化条件下，其效率可超越反向传播，这使得 PCNs 成为大规模应用与神经形态硬件领域颇具前景的替代方案。此外，从数学角度可将 PCNs 视为传统 FNNs 的超集，这显著扩展了监督与非监督学习中可能的架构范围。本文对 PCNs 进行了全面综述与形式化规范，特别将其置于现代 ML 方法的背景下进行探讨，并论证 PC 作为一种通用且前景广阔的框架，值得 ML 社区进一步深入研究。