2004/12/24 by B. V. Kryzhanovsky, Boris Kryzhanovsky, Leonid Litinskii +6
Computer Science · Neuroscience · Physics and Astronomy · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #Neural dynamics and brain function #cond-mat.dis-nn
paper · pdf · doi:10.48550/arxiv.cond-mat/0412680
6 pages, Lecture on International Joint Conference on Neural Networks IJCNN-2004
arxiv created 2004/12/24 · openalex publication_date 2004/12/24 · arxiv updated 2009/12/01 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28
We consider two models of Hopfield-like associative memory with q-valued neurons: Potts-glass neural network (PGNN) and parametrical neural network (PNN). In these models neurons can be in more than two different states. The models have the record characteristics of its storage capacity and noise immunity, and significantly exceed the Hopfield model. We present a uniform formalism allowing us to describe both PNN and PGNN. This networks inherent mechanisms, responsible for outstanding recognizing properties, are clarified.