A class of neural network with nonsymmetrical connections is considered. The analysis of the dynamical behavior shows that this type of neural network is characterized by a unique equilibrium point whose attraction domain is the entire space. Such properties do not depend on the shape of neuron nonlinearities. Application of this class of neural networks to the A/D conversion is considered and design procedures for an A/D converter are illustrated. Finally, computer simulations and experimental results obtained with a discrete component prototype of the converter are presented.
On a class of nonsymmetrical neural network with applications to ADC / G. Avitabile; M. Forti; S. Manetti; M. Marini. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY. - ISSN 1051-8215. - STAMPA. - 38:(1991), pp. 202-209. [10.1109/31.68298]
On a class of nonsymmetrical neural network with applications to ADC
MANETTI, STEFANO;MARINI, MAURO
1991
Abstract
A class of neural network with nonsymmetrical connections is considered. The analysis of the dynamical behavior shows that this type of neural network is characterized by a unique equilibrium point whose attraction domain is the entire space. Such properties do not depend on the shape of neuron nonlinearities. Application of this class of neural networks to the A/D conversion is considered and design procedures for an A/D converter are illustrated. Finally, computer simulations and experimental results obtained with a discrete component prototype of the converter are presented.I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.