Optimization of feedforward neural networks

Engineering Applications of Artificial Intelligence

Volumn 9, Issue 2, 1996, Pages 109-119

  Han, Jun ^a   Moraga, Claudio ^b   Sinne, Stefan ^b  

^a TU DORTMUND UNIVERSITY   (Germany)

^b NONE

Author keywords

Feedforward neural networks; Parametric nets; Soft computing

Indexed keywords

BACKPROPAGATION; ERRORS; GENETIC ALGORITHMS; LEARNING SYSTEMS; OPTIMIZATION; OSCILLATIONS;

ACTIVATION FUNCTION; BACKPROPAGATION ALGORITHM; PARAMETRIC NETS; SOFT COMPUTING; VARIANT SIGMOID FUNCTION;

FEEDFORWARD NEURAL NETWORKS;

EID: 0030121137     PISSN: 09521976     EISSN: None     Source Type: Journal    
DOI: 10.1016/0952-1976(95)00001-1     Document Type: Article

References (18)

1. Hecht-Nielsen R. Neurocomputing. Addison-Wesley, Reading, MA (1990).
2. Hertz J., Krogh A. and Palmer R. G. Introduction to the Theory of Neural Computation. Addison-Wesley, Reading, MA (1991).
3. Fahlman S. E. An empirical study of learning speed in back-propagation networks. Technical Report CMU-CS-88-162, CMU (1988).
4. Fahlman S. E. and Lebiere C. The cascade-correlation learning architecture. In Advances in Neural Information Processing Systems 2 (Edited by Touretzky). Morgan-Kaufmann (1990).
5. Hornik K., Stinchcombe M. and White H. Multilayer feedforward networks are universal approximators. Neural Networks 2, 359-366 (1989).
6. Kosko B. Neural Networks and Fuzzy Systems. Prentice-Hall, Englewood Cliffs, NJ (1992).
7. Grefenstette J. J. Optimization of control parameters for genetic algorithms. IEEE Trans. Syst. Man, Cyber. SMC-16, 122-128 (1986).
8. Haykin S. Neural Networks: A Comprehensive Foundation. Macmillan College Publishing Co. (1994).
9. Little W. A. The existence of persistent states in the brain. Math. Biosci. 19, 101 (1974).
10. Little W. A. and Shaw G. L. Analytic study of the memory capacity of a neural network. Math. Biosci. 39, 281 (1978).
11. Müller B. and Reinhardt J. Neural Networks. Springer, Berlin (1990).
12. Han J. and Moraga C. Hybrid nets with variable parameters: a novel approach to fast learning under backpropagation. Proc. First Int. IEEE Symp. on Intelligence in Neural and Biological Systems. IEEE-CS-Press (1995).
13. Han J. and Moraga C. The influence of the sigmoid function parameters on the speed of backpropagation learning. In From Natural to Artificial Neural Computation (Edited by Mira and Sandoval), pp. 195-201. Springer, Berlin (1995).
14. Han J., Sinne S. and Moraga C. Optimization of dynamical parameters for neural networks with sigmoid activation functions. Proc. 14th Int. Congress on Cybernetics (1995).
15. Morabito F. C. Fast backpropagation using modified sigmoidal functions. Proc. Int. Conf. on Artificial Neural Networks, pp. 537-540. Springer, Berlin (1994).
16. Stornetta W. S. and Huberman B. A. An improved three-layer, back propagation algorithm. IEEE First Int. Conf. on Neural Networks (1987).
17. Goldberg D. E. Genetic Algorithm in Search, Optimization, and Machine Learning. Addison-Wesley, Reading, MA (1989).
18. Lan K. J. and Witbrock M. J. Learning to tell two spirals apart. In Proc. 1988 Connectionist Models Summer School, San Mateo, pp. 52-59. Morgan-Kaufmann (1989).