arXiv · cond-mat/9901251
Fixed points of Hopfield type neural networks
Abstract
The set of the fixed points of the Hopfield type network is under investigation. The connection matrix of the network is constructed according the Hebb rule from the set of memorized patterns which are treated as distorted copies of the standard-vector. It is found that the dependence of the set of the fixed points on the value of the distortion parameter can be described analytically. The obtained results are interpreted in the terms of neural networks and the Ising model at T=0.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Leonid B. Litinskii. 1999-01-23. Fixed points of Hopfield type neural networks. https://arxiv.org/abs/cond-mat/9901251
Cite the original work for its findings. Save a collection to share your selection of sources.