Serviços Personalizados
Journal
Artigo
Indicadores
- Citado por SciELO
- Acessos
Links relacionados
- Similares em SciELO
Compartilhar
Revista mexicana de física
versão impressa ISSN 0035-001X
Resumo
VEGA, J.J; REYNOSO, R e CARRILLO CALVET, H. Learning limits of an artificial neural network. Rev. mex. fis. [online]. 2008, vol.54, suppl.1, pp.22-29. ISSN 0035-001X.
Technological advances in hardware as well as new computational paradigms give us the opportunity to apply digital techniques to Pulse Shape Analysis (PSA), requiring powerful resources. In this paper, we present a PSA application based on Artificial Neural Networks (ANNs). These adaptive systems offer several advantages for these tasks; nevertheless it is necessary to face the particular problems linked to them as: the selection of the learning rule and the ANN architecture, the sizes of the training and validation data sets, overtraining, the effect of noise on the pattern identification ability, etc. We will present evidences of the effect on the performance of a back-propagation ANN as a pattern identifier of both: the size of the noise that the Bragg curve spectrometer signal present and of overtraining. In fact, these two effects are related.
Palavras-chave : Neural networks; Bragg curve spectroscopy; digital pulse-shape analysis; pattern identification.