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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
K-way energy probes in discriminative PCNs reduce to a monotone function of the log-softmax margin plus an untrained residual and empirically track below softmax on CIFAR-10.
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.
-
K-Way Energy Probes for Metacognition Reduce to Softmax in Discriminative Predictive Coding Networks
K-way energy probes in discriminative PCNs reduce to a monotone function of the log-softmax margin plus an untrained residual and empirically track below softmax on CIFAR-10.