Necessary and sufficient condition for absolute stability of neural networks
Mauro Forti, S. Manetti, Mauro Marini · IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications · 1994
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.>