arXiv AI September 2, 2026 By Xueyuan Li, Danilo Vasconcellos Vargas

A Study of Hidden-State Optimization Order in Predictive Coding Networks

The paper investigates how the sequence of hidden-state optimization affects feature learning in local-learning models, specifically predictive coding networks (PCNs). It introduces a boundary-first inference schedule that first aligns hidden states at chunk boundaries before refining representations within each chunk. Experiments on CIFAR-10 show that this approach improves accuracy by 9.77% over standard PCNs and 5.51% under a different parametrization, with diagnostics indicating stronger feature learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Sep 1

A Study of Hidden-State Optimization Order in Predictive Coding Networks

Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning in deep networks. We study whether the order of hid...

Hugging Face Trending Papers

Jun 22

Error Highways: Scaling Predictive Coding to Very Deep Networks

Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, they have remained largely confined to shallow architectures and evaluated on simple machine intelligence benchmarks.

benchmarks

arXiv Machine Learning

Jun 26

Learning Long-Range Dependencies with Temporal Predictive Coding

arXiv:2602. 18131v2 Announce Type: replace Abstract: Temporal Predictive Coding provides a layer-local, parallelisable mechanism for learning in recurrent systems, making it an attractive candidate for online local learning on neuromorphic and edge hardware.

By Tom Potter, Oliver Rhodes

benchmarks

arXiv AI

Aug 11

On the Infinite Width and Depth Limits of Predictive Coding Networks

arXiv:2602. 07697v3 Announce Type: replace-cross Abstract: Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network activities before updating weights.

By Francesco Innocenti, El Mehdi Achour, Rafal Bogacz

llms safety

arXiv Machine Learning

Sep 21

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks

arXiv:2609.21583v1 Announce Type: cross Abstract: Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redund...

By Aidin Attar, Michele Rossi

arXiv Machine Learning

Jun 30

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.

By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen

benchmarks safety

One email a morning, machine-written

Related stories

A Study of Hidden-State Optimization Order in Predictive Coding Networks

Error Highways: Scaling Predictive Coding to Very Deep Networks

Learning Long-Range Dependencies with Temporal Predictive Coding

On the Infinite Width and Depth Limits of Predictive Coding Networks

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization