Ruano, Antonio2013-02-112013-02-111996Ruano, A. E. Training Multilayer Perceptrons - an Optimization Perspective, Trabalho apresentado em 2º Encontro Português de Controlo Automático (Controlo’ 96), In 2º Encontro Português de Controlo Automático (Controlo’ 96), Porto, 1996.AUT: ARU00698;http://hdl.handle.net/10400.1/2280Multilayer perceptrons (MLPs) (1) are the most common artificial neural networks employed in a large field of applications. In control and signal processing applications, MLPs are mainly used as nonlinear mapping approximators. The most common training algorithm used with MLPs is the error back-propagation (BP) alg. (1).engconference object2013-01-28