A two-layer Hebbian network learns manifold structure through overlapping channels and propagates sparse labels across those channels, enabling online semi-supervised classification without an explicit adjacency graph.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Neural Network for Semi-Supervised Learning on Manifolds
A two-layer Hebbian network learns manifold structure through overlapping channels and propagates sparse labels across those channels, enabling online semi-supervised classification without an explicit adjacency graph.