Fermi-Bose Machine

arXiv:2404.13631v1 Announce Type: new
Abstract: Distinct from human cognitive processing, deep neural networks trained by backpropagation can be easily fooled by adversarial examples. To design a semantically meaningful representation learning, we discard backpropagation, and instead, propose a local contrastive learning, where the representation for the inputs bearing the same label shrink (akin to boson) in hidden layers, while those of different labels repel (akin to fermion). This layer-wise learning is local in nature, being biological plausible. A statistical mechanics analysis …

abstract adversarial adversarial examples arxiv backpropagation cognitive cond-mat.dis-nn cond-mat.stat-mech cs.lg cs.ne design examples hidden human inputs machine networks neural networks processing q-bio.nc representation representation learning type