A sufficient condition is proved guaranteeing that a class of neural circuits that includes the Hopfield model as a special case is globally convergent towards a unique stable equilibrium. The condition only requires symmetry and negative semi-definiteness of the neuron connection matrix T and is extremely simple to check and apply in practice. The consequences of the above result are discussed in the context of neural circuits for optimization of quadratic cost functions. © 1992 IEEE
Forti, M., Manetti, S., Marini, M. (1992). A condition for global convergence of a class of symmetric neural circuits. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I. FUNDAMENTAL THEORY AND APPLICATIONS, 39(6), 480-483 [10.1109/81.153645].
A condition for global convergence of a class of symmetric neural circuits
Forti M.;
1992-01-01
Abstract
A sufficient condition is proved guaranteeing that a class of neural circuits that includes the Hopfield model as a special case is globally convergent towards a unique stable equilibrium. The condition only requires symmetry and negative semi-definiteness of the neuron connection matrix T and is extremely simple to check and apply in practice. The consequences of the above result are discussed in the context of neural circuits for optimization of quadratic cost functions. © 1992 IEEE
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/2668
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo