Multi-state neural networks based upon spin-glasses: a biased overview
Disordered Systems and Neural Networks
2007-05-23 v1 Statistical Mechanics
q-bio
Abstract
Recent results are reviewed on both the time evolution and retrieval properties of multi-state neural networks that are based upon spin-glass models. In particular, the properties of models with neuron states having Q-Ising symmetry are discussed for various architectures. The main common features and differences are highlighted.
Cite
@article{arxiv.cond-mat/0307104,
title = {Multi-state neural networks based upon spin-glasses: a biased overview},
author = {D. Bolle},
journal= {arXiv preprint arXiv:cond-mat/0307104},
year = {2007}
}
Comments
Review chapter to appear in Advances in Condensed Matter and Statistical Mechanics, ed. by E. Korutcheva and R. Cuerno, Nova Science Publishers (38 pages Latex with 12 eps-figures)