Title :
Necessary and sufficient condition for absolute stability of neural networks
Author :
Forti, Mauro ; Manetti, Stefano ; Marini, Mauro
Author_Institution :
Dept. of Electron. Eng., Florence Univ., Italy
fDate :
7/1/1994 12:00:00 AM
Abstract :
The main result in this paper is that for a neural circuit of the Hopfield type with a symmetric connection matrix T, the negative semidefiniteness of T is a necessary and sufficient condition for Absolute Stability. The most significant theoretical implication is that the class of neural circuits with a negative semidefinite T is the largest class of circuits that can be employed for embedding and solving optimization problems without the risk of spurious responses
Keywords :
Hopfield neural nets; matrix algebra; optimisation; stability; Hopfield neural circuit; absolute stability; embedding; negative semidefiniteness; neural networks; optimization problems; spurious responses; symmetric connection matrix; Circuit stability; Hopfield neural networks; Integrated circuit interconnections; Neural networks; Neurons; Sampling methods; Shape; Sufficient conditions; Symmetric matrices; Traveling salesman problems;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
