Idioma:

Nonstationary Time Series Prediction Using Local Models Based on Competitive Neural Networks

Barreto, Guilherme A. ; Mota, João C. M. ; Souza, Luis G. M. ; Frota, Rewbenio A.

Innovations in Applied Artificial Intelligence, 2004, p.1146-1155 [Periódico revisado por pares]

Berlin, Heidelberg: Springer Berlin Heidelberg

Texto completo disponível

Citações Citado por

Enviar para

Título:
Nonstationary Time Series Prediction Using Local Models Based on Competitive Neural Networks
Autor: Barreto, Guilherme A. ; Mota, João C. M. ; Souza, Luis G. M. ; Frota, Rewbenio A.
Assuntos: Applied sciences ; Artificial intelligence ; Computer science; control theory; systems ; Data processing. List processing. Character string processing ; Exact sciences and technology ; Input Vector ; Learning and adaptive systems ; Local Model ; Memory organisation. Data processing ; Normalize Root Mean Square Error ; Prediction Task ; Software ; Weight Vector
É parte de: Innovations in Applied Artificial Intelligence, 2004, p.1146-1155
Notas: SourceType-Conference Papers & Proceedings-1
ObjectType-Conference Paper-1
content type line 25
Descrição: In this paper, we propose a general approach for the application of competitive neural networks to nonstationary time series prediction. The underlying idea is to combine the simplicity of the standard least-squares (LS) parameter estimation technique with the information compression power of unsupervised learning methods. The proposed technique builds the regression matrix and the prediction vector required by the LS method through the weight vectors of the K first winning neurons (i.e. those most similar to the current input vector). Since only few neurons are used to build the predictor for each input vector, this approach develops local representations of a nonstationary time series suitable for prediction tasks. Three competitive algorithms (WTA, FSCL and SOM) are tested and their performances compared with the conventional approach, confirming the efficacy of the proposed method.
Editor: Berlin, Heidelberg: Springer Berlin Heidelberg
Idioma: Inglês

Links

View record in Pascal Francis

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Nonstationary Time Series Prediction Using Local Models Based on Competitive Neural Networks

Barreto, Guilherme A. ; Mota, João C. M. ; Souza, Luis G. M. ; Frota, Rewbenio A.

Berlin, Heidelberg: Springer Berlin Heidelberg

Buscando em bases de dados remotas. Favor aguardar.