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.

Necessary and sufficient conditions for absolute stability of neural networks / FORTI M.; S. MANETTI; MARINI M.. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I. FUNDAMENTAL THEORY AND APPLICATIONS. - ISSN 1057-7122. - STAMPA. - Vol. 41, no. 7:(1994), pp. 491-494. [10.1109/81.298364]

Necessary and sufficient conditions for absolute stability of neural networks

MANETTI, STEFANO;MARINI, MAURO
1994

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.
1994
Vol. 41, no. 7
491
494
FORTI M.; S. MANETTI; MARINI M.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/215340
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 185
  • ???jsp.display-item.citation.isi??? 171
social impact