A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks

Abstract

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstable. In this work, we show how by simply changing the temporal scheduling of the update rule for the synaptic weights leads to an algorithm that is much more efficient and stable than the original one, and has theoretical guarantees in terms of convergence. The proposed algorithm, that we call incremental predictive coding (iPC) is also more biologically plausible than the original one, as it it fully automatic. In an extensive set of experiments, we show that iPC constantly performs better than the original formulation on a large number of benchmarks for image classification, as well as for the training of both conditional and masked language models, in terms of test accuracy, efficiency, and convergence with respect to a large set of hyperparameters.

Download paper here

BibTex

@inproceedings{ salvatori2024a, title={A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks}, author={Tommaso Salvatori and Yuhang Song and Yordan Yordanov and Beren Millidge and Lei Sha and Cornelius Emde and Zhenghua Xu and Rafal Bogacz and Thomas Lukasiewicz}, booktitle={The Twelfth International Conference on Learning Representations (ICLR)}, year={2024}, url={https://openreview.net/forum?id=RyUvzda8GH} }