NeuroCOLT

Neural Networks and Computational Learning Theory

About NeuroCOLT

Papers Archive

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-95-027

A characterization of the existence of energies for neural networks

Michel Cosnard
LIP, ENS, Lyon, France

Eric Gole
Universidad de Chile, Santiago, Chile

Abstract
In this paper we give under an appropriate theoretical framework a characterization about neural networks which admit an energy. We prove that a neural network admits an energy if and only if the weight matrix verifies two conditions: the diagonal elements are non-negative and the associated incidence graph does not admit non-quasi-symmetric circuits.

Download Compressed Postscript