Learning neural networks with noisy inputs using the errors-in-variables approach.
IEEE Trans Neural Netw
; 11(2): 402-14, 2000.
Article
en En
| MEDLINE
| ID: mdl-18249770
Currently, most learning algorithms for neural-network modeling are based on the output error approach, using a least squares cost function. This method provides good results when the network is trained with noisy output data and known inputs. Special care must be taken, however, when training the network with noisy input data, or when both inputs and outputs contain noise. This paper proposes a novel cost function for learning NN with noisy inputs, based on the errors-in-variables stochastic framework. A learning scheme is presented and examples are given demonstrating the improved performance in neural-network curve fitting, at the cost of increased computation time.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Tipo de estudio:
Prognostic_studies
Idioma:
En
Revista:
IEEE Trans Neural Netw
Asunto de la revista:
INFORMATICA MEDICA
Año:
2000
Tipo del documento:
Article
País de afiliación:
Bélgica
Pais de publicación:
Estados Unidos