Improving generalization of MLPs with sliding mode control and the Levenberg-Marquardt algorithm

Neurocomputing

Volumn 70, Issue 7-9, 2007, Pages 1342-1347

  Costa, Marcelo Azevedo ^a   Braga, Antônio de Pádua ^a   Menezes, Benjamin Rodrigues de ^a  

^a FEDERAL UNIVERSITY OF MINAS GERAIS   (Brazil)

Author keywords

Generalization; Levenberg marquardt; Multi layer perceptron; Multi objective

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; SLIDING MODE CONTROL; VECTORS;

GENERALIZATION; LEVENBERG-MARQUARDT ALGORITHM; MULTI-OBJECTIVE;

MULTILAYER NEURAL NETWORKS;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER PROGRAM; CONTROLLED STUDY; INTERMETHOD COMPARISON; MATHEMATICAL COMPUTING; NORMAL DISTRIBUTION; PRIORITY JOURNAL; PROCESS OPTIMIZATION; VALIDATION STUDY;

EID: 33847359184     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.09.003     Document Type: Article

References (11)

1. Bartlett P.L. For valid generalization, the size of the weights is more important than the size of the network. In: Mozer M.C., Jordan M.I., and Petsche T. (Eds). Advances in Neural Information Processing Systems vol. 9 (1997), MIT Press, Cambridge, MA 134-140
2. Bazaraa M.S., Sherali H.D., and Shetty C.M. Nonlinear Programming: Theory and Algorithms. second ed. (January 1993), Wiley, New York
3. M.A. Costa, A.P. Braga, B.R. Menezes, R.A. Teixeira, G.G. Parma, Training neural networks with a multi-objective sliding mode control algorithm, Neurocomputing (51) (2003) 467-473.
4. Geman S., Bienenstock E., and Doursat R. Neural networks and the bias/variance dilemma. Neural Comput. 4 1 (1992) 158
5. Hagan M.T., and Menhaj M.B. Training feedforward networks with the marquardt algorithm. IEEE Trans. Neural Networks 5 6 (1994) 989-993
6. Marquardt D.W. An algorithm for least squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 11 2 (1963) 431-441
7. Parma G.G., de Menezes B.R., and Braga A.P. Neural networks learning with sliding mode control: the sliding mode backpropagation algorithm. Int. J. Neural Syst. 9 3 (1999) 187-193
8. Reed R. Pruning algorithms-a survey. IEEE Trans. Neural Networks 4 5 (1993) 740-746
9. Stone M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. B 36 (1974) 111-133
10. Teixeira R.A., Braga A.P., Takahashi R.H.C., and Saldanha R.R. Improving generalization of MLPs with multi-objective optimization. Neurocomputing 35 14 (2000) 189-194
11. Weigend A.S., Huberman B.A., and Rumelhart D.E. Predicting the future: a connectionist approach. Int. J. Neural Syst. 1 (1990) 193-209