This paper considers the feed-forward training problem from the numerical point of view, in particular the conditioning of the problem. It is well known that the feed-forward training problem is often ill-conditioned; this affects the behaviour of training algorithms, the choice of such algorithms and the quality of the solutions achieved. A geometric interpretation of ill-conditioning is explored and an example of function approximation is analysed in detail. This paper considers the feed-forward training problem from the numerical point of view, in particular the conditioning of the problem. It is well known that the feed-forward training problem is often ill-conditioned; this affects the behaviour of training algorithms, the choice of such algorithms and the quality of the solutions achieved. A geometric interpretation of ill-conditioning is explored and an example of function approximation is analyzed in detail
Citazione: | McKeown, J.J., Stella, F.A., & Hall, G. (1997). Some numerical aspects of the training problem for feed-forward neural nets. NEURAL NETWORKS, 10(8), 1455-1463. |
Tipo: | Articolo in rivista - Articolo scientifico |
Carattere della pubblicazione: | Scientifica |
Presenza di un coautore afferente ad Istituzioni straniere: | Si |
Titolo: | Some numerical aspects of the training problem for feed-forward neural nets |
Autori: | McKeown, JJ; Stella, FA; Hall, G |
Autori: | |
Data di pubblicazione: | 1997 |
Lingua: | English |
Rivista: | NEURAL NETWORKS |
Digital Object Identifier (DOI): | 10.1016/S0893-6080(97)00015-4 |
Appare nelle tipologie: | 01 - Articolo su rivista |