SOURCE-LINKED INTELLIGENCE

Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Overparameterized neural networks carry far more hidden units than a task nominally requires, raising the question of which neurons are essential and whether that distinction is legible in the representation itself, without labels or gradients. We cast neuron selection as the problem of coarse-graining the hidden layer by retaining a subset of its neurons, and score each putative selection by the mapping entropy (ME). This quantity measures the loss of discriminatory power inherent in discarding part of the network neurons, and the selection that minimises the ME is taken as particularly infor

Read original source ↗ Open in workspace

recordType

paper

region

Global