Predictive Coding
Overview
Predictive coding studies how systems can infer, learn, or compress information by predicting incoming data and correcting mismatches. In neuroscience, hierarchical Bayesian and free-energy models use precision-weighted prediction errors to explain perception and action; in machine learning, predictive coding networks use local updates, while equilibrium propagation, feedback pathways, and amortized inference aim to make training faster and deeper. Related predictive methods forecast future inputs or code residuals for tasks such as video, language, and data compression, with evaluations spanning CIFAR and ImageNet, time-series benchmarks, and alignment to visual-cortex responses. A central tension is whether local, biologically inspired computation can match backpropagation and scale to deep or long-range tasks without giving up efficiency or hardware simplicity.
Latest papers
59 papers6 papers in the last four weeks, up 20% on the four weeks before. 0.0% of all new papers.