Energy functional and fixed points of a neural network

1997/06/27 by Leonid B. Litinskii, Litinskii, Leonid B.
Physics and Astronomy · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #cond-mat.dis-nn

paper · pdf · doi:10.48550/arxiv.cond-mat/9706280

LaTex, 7 pages, e-mail: [email protected]

arxiv created 1997/06/27 · arxiv updated 2012/03/24

Abstract

A dynamic system, which is used in the neural network theory, Ising spin glasses and factor analysis, has been investigated. The properties of the connection matrix, which guarantee the coincidence of the set of the fixed points of the dynamic system with the set of the local minima of the energy functional, have been determined. The influence of the connection matrix diagonal elements on the structure of the fixed points set has been investigated.

Related

• Energy Functional and Fixed Points of a Neural Networks
• Fixed points of Hopfield type neural networks
• Some Exact Results of Hopfield Neural Networks and Applications
• Highly Symmetric Neural Networks of Hopfield Type (exact results)
• Linear Algebra and Duality of Neural Networks