English

Predictive Coding Graphs are a Superset of Feedforward Neural Networks

Machine Learning 2026-03-09 v1 Disordered Systems and Neural Networks Artificial Intelligence Neural and Evolutionary Computing Machine Learning

Abstract

Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons). This positions PCNs more strongly within contemporary machine learning (ML), and reinforces earlier proposals to study the use of non-hierarchical neural networks for ML tasks, and more generally the notion of topology in neural networks.

Keywords

Cite

@article{arxiv.2603.06142,
  title  = {Predictive Coding Graphs are a Superset of Feedforward Neural Networks},
  author = {Björn van Zwol},
  journal= {arXiv preprint arXiv:2603.06142},
  year   = {2026}
}

Comments

11 pages, 3 figures. Accepted at the NeuroAI Workshop @ NeurIPS 2024. OpenReview: https://openreview.net/forum?id=J36z3R0sNq

R2 v1 2026-07-01T11:06:35.305Z