论文信息 - Training neural networks with a multi-objective sliding mode control algorithm

Training neural networks with a multi-objective sliding mode control algorithm

Abstract This paper presents a new sliding mode control algorithm that is able to guide the trajectory of a multi-layer perceptron within the plane formed by the two objective functions: training set error and norm of the weight vectors. The results show that the neural networks obtained are able to generate an approximation to the Pareto set, from which an improved generalization performance model is selected.

Antônio de Pádua Braga | Marcelo Azevedo Costa | Roselito de Albuquerque Teixeira | Benjamin Rodrigues de Menezes | Gustavo Guimarães Parma

[1] Elie Bienenstock,et al. Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[2] Vadim I. Utkin,et al. Sliding Modes and their Application in Variable Structure Systems , 1978 .

[3] C. Hwang,et al. Fuzzy Multiple Objective Decision Making: Methods And Applications , 1996 .

[4] Peter L. Bartlett,et al. For Valid Generalization the Size of the Weights is More Important than the Size of the Network , 1996, NIPS.

[5] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[6] Antônio de Pádua Braga,et al. Sliding mode algorithm for training multilayer artificial neural networks , 1998 .

[7] Ricardo H. C. Takahashi,et al. Improving generalization of MLPs with multi-objective optimization , 2000, Neurocomputing.

[8] Antônio de Pádua Braga,et al. Neural Networks Learning with Sliding Mode Control: The Sliding Mode Backpropagation Algorithm , 1999, Int. J. Neural Syst..