<ul><li>Bayesian Predictive Coding (BPC) is a Bayesian extension to the influential theory of Predictive Coding (PC) in information processing in the brain.</li><li>BPC estimates a posterior distribution over network parameters, allowing for better quantification of epistemic uncertainty.</li><li>Compared to PC, BPC converges in fewer epochs in the full-batch setting and remains competitive in the mini-batch setting.</li><li>BPC provides a biologically plausible method for Bayesian learning in the brain and offers attractive uncertainty quantification in deep learning.</li></ul>

Bayesian Predictive Coding

Discover more