all AI news
Fermi-Bose Machine
April 23, 2024, 4:41 a.m. | Mingshan Xie, Yuchen Wang, Haiping Huang
cs.LG updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne