A new formulation of the learning problem for a neural network controller

Autoria(s): Ruano, A. E.; Jones, D. I.; Fleming, P. J.
Data(s)

11/02/2013

11/02/2013

1991

28/01/2013
Identificador

Ruano, A. E. B.; Jones, D. I; Fleming, P. J. A New Formulation of the Learning Problem for a Neural Network Controller, Trabalho apresentado em 30th IEEE Conference on Decision and Control, In 30th IEEE Conference on Decision and Control, Brighton, 1991.

AUT: ARU00698;

http://hdl.handle.net/10400.1/2279
Idioma(s)

eng
Direitos

restrictedAccess
Tipo

conferenceObject
Resumo

In this paper we consider the learning problem for a class of multilayer perceptrons which is practically relevant in control systems applications. By reformulating this problem, a new criterion is developed, which reduces the number of iterations required for the learning phase.
Acesso ao item digital