Closed-form predictive coding via hierarchical Gaussian filters

arXiv cs.LG Papers

Summary

The paper introduces closed-form predictive coding via hierarchical Gaussian filters that restore precision-weighted prediction errors, yielding faster and more efficient training without global error signals, outperforming backpropagation on certain tasks.

arXiv:2605.20293v1 Announce Type: new Abstract: Predictive coding (PC) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to date, it remains slower, and performance degrades sharply as network depth increases. We trace both problems to a single simplification: current PC networks fix the precision matrix to the identity, discarding precision-weighted prediction errors that the variational derivation requires to be fast, local, and Bayesian. We close this gap by expressing predictive coding networks as deep hierarchical Gaussian filters (HGFs) and restore precision-weighted message passing, yielding dynamic uncertainty estimates and Hebbian-compatible update rules at every layer. The resulting networks can simultaneously learn activations, weights, and precisions under a single free-energy objective, with no global error signal, and resolve inference without requiring iterations or automatic differentiation. On FashionMNIST, our solution approaches backpropagation in epoch-level wall-clock cost while converging in fewer epochs, and outperforms it on online, data efficiency, and concept-drift tasks. We thus establish that closed-form variational inference with online precision learning provides a tractable foundation for deep predictive coding networks, retaining biological and interpretative advantages, without requiring iterative relaxation or global error signals.
Original Article
View Cached Full Text

Cached at: 05/21/26, 06:21 AM

# Closed-form predictive coding via hierarchical Gaussian filters
Source: [https://arxiv.org/abs/2605.20293](https://arxiv.org/abs/2605.20293)
[View PDF](https://arxiv.org/pdf/2605.20293)

> Abstract:Predictive coding \(PC\) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to date, it remains slower, and performance degrades sharply as network depth increases\. We trace both problems to a single simplification: current PC networks fix the precision matrix to the identity, discarding precision\-weighted prediction errors that the variational derivation requires to be fast, local, and Bayesian\. We close this gap by expressing predictive coding networks as deep hierarchical Gaussian filters \(HGFs\) and restore precision\-weighted message passing, yielding dynamic uncertainty estimates and Hebbian\-compatible update rules at every layer\. The resulting networks can simultaneously learn activations, weights, and precisions under a single free\-energy objective, with no global error signal, and resolve inference without requiring iterations or automatic differentiation\. On FashionMNIST, our solution approaches backpropagation in epoch\-level wall\-clock cost while converging in fewer epochs, and outperforms it on online, data efficiency, and concept\-drift tasks\. We thus establish that closed\-form variational inference with online precision learning provides a tractable foundation for deep predictive coding networks, retaining biological and interpretative advantages, without requiring iterative relaxation or global error signals\.

## Submission history

From: Nicolas Legrand \[[view email](https://arxiv.org/show-email/2df1f913/2605.20293)\] **\[v1\]**Tue, 19 May 2026 10:11:41 UTC \(947 KB\)

Similar Articles

Efficient Bayesian Deep Ensembles via Analytic Predictive Inference

arXiv cs.LG

Introduces an efficient Bayesian deep ensemble method for predictive regression that combines low-dimensional ensemble representation, closed-form Bayesian aggregation, and independent ensemble training to achieve calibrated uncertainty estimates with computational efficiency.

Online Localized Conformal Prediction

arXiv cs.LG

This paper proposes Online Localized Conformal Prediction (OLCP) to address covariate heterogeneity in online learning and time-series settings. It introduces OLCP-Hedge for bandwidth selection and demonstrates valid long-run coverage with narrower prediction sets compared to existing baselines.