3 papers
cs.LG2026
Closed-form predictive coding via hierarchical Gaussian filters
Aleksandrs Baskakovs, Sylvain Estebe, Kenneth Enevoldsen +3
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 pe…
cs.LG2026
Robust volatility updates for Hierarchical Gaussian Filtering
Christoph Mathys, Nicolas Legrand, Peter Thestrup Waade +2
Hierarchical Gaussian Filtering (HGF) networks allow for efficient updating of posterior distributions (beliefs) about hidden states of an agent's environment. HGF parent nodes can…
cs.NE2025
pyhgf: A neural network library for predictive coding
Nicolas Legrand, Lilian Weber, Peter Thestrup Waade +4
Bayesian models of cognition have gained considerable traction in computational neuroscience and psychiatry. Their scopes are now expected to expand rapidly to artificial intellige…