Avoiding False Local Minima by Proper Initialization of Connections

IEEE Transactions on Neural Networks

Volumn 3, Issue 6, 1992, Pages 899-905

  Wessels, Lodewyk F A ^a   Barnard, Etienne ^b  

^a Division for Materials Science and Technology ^*  (United States)

^b UNIVERSITY OF PRETORIA   (South Africa)

Author keywords

[No Author keywords available]

Indexed keywords

OPTIMIZATION;

CLASSIFIER DEFECTS; LOCAL MINIMA;

NEURAL NETWORKS;

EID: 0026955395     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.165592     Document Type: Article

References (8)

1. L.F. A. Wessels, E. Barnard and E. van Rooyen, “The physical correlates of local minima,” in Proc. Int. Neural Network Conf. (Paris), July 1990.
2. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing. Cambridge MA: MIT Press, 1986, ch. 8, pp. 318-362.
3. R. L. Watrous, “Learning algorithms for connectionist networks: applied gradient methods of Nonlinear optimization,” in Proc. Int. Conf. Neural Networks (San Diego, CA), July 1987, pp. II-619-II-627.
4. M. Stinchcombe and H. White, “Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions,” in Proc. Int. Conf. Neural Networks (Washington DC), June 1989, pp. 1-613-1-618.
5. D. H. Ackley, G. E. Hinton, and T. J. Sejnowski, “A learning algorithm for Boltzmann machines,” Cognitive Science, vol. 9, pp. 147-169, 1985.
6. S.A. Solla, E. Levin, and M. Fleisher, “Accelerated learning in layered neural networks,” Tech. Rep., AT&T Bell Laboratories, 1988.
7. M.J.D. Powell, “Restart procedures for the conjugate-gradient method,” Mathematical Programming, vol. 12, pp. 241-254, 1977.
8. E. Barnard and D. Casasent, “A comparison between criterion functions for linear classifiers with an application to neural nets,” IEEE Trans. Syst., Man, Cybern., to be published.