On-line neural training algorithm with sliding mode control and adaptive learning rate

Neurocomputing

Volumn 70, Issue 16-18, 2007, Pages 2687-2691

  Nied, A ^a   Seleme Jr , S I ^b   Parma, G G ^b   Menezes, B R ^b  

^a SANTA CATARINA STATE UNIVERSITY   (Brazil)

^b FEDERAL UNIVERSITY OF MINAS GERAIS   (Brazil)

Author keywords

Multilayer perceptron; Neural networks; On line learning algorithm; Sliding modes

Indexed keywords

ADAPTIVE CONTROL SYSTEMS; LEARNING ALGORITHMS; SLIDING MODE CONTROL; SYSTEM STABILITY;

NEURAL TRAINING; VARIABLE STRUCTURE SYSTEM;

MULTILAYER NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; COMPUTER SYSTEM; CONTROLLED STUDY; LEARNING ALGORITHM; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; NORMAL DISTRIBUTION; ONLINE SYSTEM; PRIORITY JOURNAL; THEORY;

EID: 34548183969     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.07.019     Document Type: Article

References (16)

1. Efe M.O., and Kaynak O. Stabilizing and robustifying the learning mechanisms of artificial neural networks in control engineering applications. Proc. Int. J. Intell. Syst. 15 5 (2000) 365-388
2. Hagan M.T., and Menhaj M.B. Training feedforward neural networks with the Marquardt algorithm. IEEE Trans. Neural Networks 5 (1994) 989-993
3. Haykin S. Neural Networks: A Comprehensive Foundation. second ed. (1999), Prentice-Hall
4. Hornik K. Multilayer feedforward networks are universal approximators. Neural Networks 2 (1989) 359-366
5. Hung J.Y., Gao W., and Hung J.C. Variable structure control: a survey. IEEE Trans. Ind. Electron. 40 (1993) 1-9
6. Kaynak O., Erbatur K., and Ertugrul M. The fusion of computationally intelligent methodologies and sliding-mode control-a survey. IEEE Trans. Ind. Electron. 48 (2001) 4-17
7. Parisi R., Di Claudio E.D., Orlandi G., and Rao B.D. A generalized learning paradigm exploiting the structure of feedforward neural networks. IEEE Trans. Neural Networks 7 (1996) 1450-1459
8. Parma G.G., Menezes B.R., and Braga A.P. Sliding mode algorithm for training multilayer artificial neural networks. Electron. Lett. 34 1 (1998) 97-98
9. Rumelhart D.E., Hinton G.E., and Williams R.J. Learning internal representations by error propagation. Parallel Distribuited Process. 1 (1986) 318-362
10. Sira-Ramirez H., and Colina-Morles E. A sliding mode strategy for adaptive learning in Adalines. IEEE Trans. Circuits Syst.-I: Fundamental Theor Appl. 42 12 (1995) 1001-1012
11. A.V. Topalov, O. Kaynak, N.G. Shakev, Variable structure systems approach for on-line learning in multilayer artificial neural networks, in: Proceedings IEEE 29th Annual Conference of the Industrial Electronics Society, 2003, pp. 2989-2994.
12. Utkin V.L. Sliding Modes and their Application in Variable Structure Systems (1978), MIR Press, Moscow
13. Yu X., Efe M.O., and Kaynak O. A general backpropagation algorithm for feedforward neural networks learning. IEEE Trans. Neural Networks 13 (2002) 251-254
14. Yu X., Zhihong M., and Rahman S.M.M. Adaptive sliding mode approach for learning in a feedforward neural networks. Neural Comput. Appl. 7 (1998) 289-294
15. Zhao Y. On-line neural network learning algorithm with exponential convergence rate. Electron. Lett. 32 15 (1996) 1381-1382
16. Zhou G., and Si J. Advanced neural network training algorithm with reduced complexity based on Jacobian deficiency. IEEE Trans. Neural Networks 9 (1998) 448-453