Alleviating ‘overfitting’ via genetically-regularised neural network
| Data(s) |
2002
|
|---|---|
| Resumo |
A hybrid genetic algorithm/scaled conjugate gradient regularisation method is designed to alleviate ANN `over-fitting'. In application to day-ahead load forecasting, the proposed algorithm performs better than early-stopping and Bayesian regularisation, showing promising initial results. |
| Identificador | |
| Publicador |
The Institution of Engineering and Technology |
| Relação |
DOI:10.1049/el:20020592 Chan, Z.S.H., Ngan, H.W., Rad, A.B., & Ho, T.K. (2002) Alleviating ‘overfitting’ via genetically-regularised neural network. Electronics Letters, 38(15), pp. 809-810. |
| Direitos |
Copyright 2002 The Institution of Engineering and Technology |
| Fonte |
Faculty of Built Environment and Engineering; School of Engineering Systems |
| Palavras-Chave | #080108 Neural Evolutionary and Fuzzy Computation #080607 Information Engineering and Theory #090607 Power and Energy Systems Engineering (excl. Renewable Power) #Neural network #System forecast |
| Tipo |
Journal Article |
