arXiv Analytics

Sign in

arXiv:cond-mat/9902123AbstractReferencesReviewsResources

Energy Functional and Fixed Points of a Neural Networks

Leonid B. Litinskii

Published 1999-02-09Version 1

It turned out that the set of the fixed points is not necessarily the same as the set of the local minima of the energy functional. It depends on the diagonal elements of the connection matrix. The simple method which allows to cut off fictitious fixed points with high energies was found out. Especially the method is effective if the connection matrix is the projection one.

Comments: RevTEX, 6 pages, one old paper
Journal: In "Neural Nets. WIRN-VIETRI-97. Proceedings of the 9th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, 22-24 May 1997", Eds. Maria Marinaro and Roberto Tagliaferri, Springer-Verlag, 1998
Categories: cond-mat.dis-nn
Related articles: Most relevant | Search more
arXiv:2409.13597 [cond-mat.dis-nn] (Published 2024-09-20)
Fluctuation-learning relationship in neural networks
arXiv:2211.07531 [cond-mat.dis-nn] (Published 2022-11-02)
On the capacity of neural networks
arXiv:2303.06375 [cond-mat.dis-nn] (Published 2023-03-11)
About the de Almeida-Thouless line in neural networks

Links

Toolbox