학술논문
Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
Document Type
article
Source
Nature Communications, Vol 7, Iss 1, Pp 1-9 (2016)
Subject
Language
English
ISSN
2041-1723
Abstract
Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules.