
FI
Francesco Innocenti
· 1 min read
ResearcharXiv cs.LG
Analog-Friendly Predictive Coding without Activation Derivatives
arXiv:2609.32350v1 Announce Type: new
Abstract: Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementation on analog hardware. However, standard nonlinear PC requires evaluating the derivative of the activation function during both inference and learning, which can be difficult to realise physically. Here, we introduce \textit{activation-matched Bregman PC}, replacing standard squared-error energies with Bregman divergences matched to the activation function. This formulation eliminates activation derivatives and, when combined with inference via mirror descent, yields local inference and learning rules requiring only weighted sums, local prediction errors, state integration, and the activation function. In digital experiments, Bregman PC performs comparably to standard PC and BP on classification and generative tasks, while preserving characteristic learning dynamics of PC and its convergence to BP under stable large-model parameterisations. These results provide a more analog-friendly formulation of nonlinear PC while retaining its key computational properties.
Original source
This story was published by arXiv cs.LG and written by Francesco Innocenti. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


