Introduction to Predictive Coding Networks for Machine Learning

2025/05/31 by Mikko Stenlund, Stenlund, Mikko
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Single-cell and spatial transcriptomics

paper · pdf · doi:10.48550/arxiv.2506.06332

openalex publication_date 2025/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Predictive coding networks (PCNs) constitute a biologically inspired framework for understanding hierarchical computation in the brain, and offer an alternative to traditional feedforward neural networks in ML. This note serves as a quick, onboarding introduction to PCNs for machine learning practitioners. We cover the foundational network architecture, inference and learning update rules, and algorithmic implementation. A concrete image-classification task (CIFAR-10) is provided as a benchmark-smashing application, together with an accompanying Python notebook containing the PyTorch implementation.

Citations

• Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks
• Predictive Coding with Spiking Neural Networks: a Survey
• A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
• A Theoretical Framework for Inference Learning
• Hybrid Predictive Coding: Inferring, Fast and Slow
• Predictive Coding: a Theoretical and Experimental Review
• Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
• World Models
• An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity
• Deep Predictive Coding Networks for Video Prediction and Unsupervised\n Learning

Related

• Predictive Coding Networks and Inference Learning: Tutorial and Survey
• Benchmarking Predictive Coding Networks -- Made Simple
• A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
• Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?
• Deep Predictive Coding Network for Object Recognition