Predictive coding is recast as deep hierarchical Gaussian filters to restore precision-weighted message passing, yielding closed-form inference and online precision learning that matches backpropagation speed on FashionMNIST while outperforming on online and concept-drift tasks.
and Bogacz, Rafal , editor =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Optimal LPC networks achieve near-minimal response times without trade-offs in energetic cost or robustness, and modular structures with reduced lateral connections match all-to-all networks in performance.
citing papers explorer
-
Closed-form predictive coding via hierarchical Gaussian filters
Predictive coding is recast as deep hierarchical Gaussian filters to restore precision-weighted message passing, yielding closed-form inference and online precision learning that matches backpropagation speed on FashionMNIST while outperforming on online and concept-drift tasks.
-
Response time of lateral predictive coding and benefits of modular structures
Optimal LPC networks achieve near-minimal response times without trade-offs in energetic cost or robustness, and modular structures with reduced lateral connections match all-to-all networks in performance.