Single State Update Predictive Coding training for Time Series Forecasting and Anomaly Detection

Researchers Matteo Cardoni and Sam Leroux introduced a training technique for Predictive Coding Networks (PCNs) that pairs a Generative PCN with a support Encoding PCN, trained in parallel to match neural activations without sequential backwards error propagation. Applied to time series anomaly detection, the approach enables more stable, continuous, online learning, addressing the main bottleneck of PCNs.

Single State Update Predictive Coding training for Time Series Forecasting and Anomaly Detection By Matteo Cardoni, Sam LerouxSource: arXiv cs.LG https://arxiv.org/list/cs.LG/recent arXiv:2608.24697v1 Announce Type: new Abstract: Predictive Coding PC is a neural learning paradigm that enables parallelizable neural network /glossary/neural-network layer updates. However, the main bottleneck of PC Networks PCN is the sequential backwards error propagation. To tackle this, we introduce a training /glossary/training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time series anomaly detection and show that our approach results in more stable, continuous, online learning.Get AI news in your inbox Daily digest of what matters in AI.