On the overtraining phenomenon of backpropagation neural networks

Mathematics and Computers in Simulation

Volumn 40, Issue 5-6 SPEC. ISS., 1996, Pages 507-521

  Tzafestas, S G ^a   Dalianis, P J ^a   Anthopoulos, G ^a  

^a NATIONAL TECHNICAL UNIVERSITY OF ATHENS   (Greece)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; BACKPROPAGATION; CHARACTER RECOGNITION; COMPUTER SIMULATION; ELECTRIC NETWORK TOPOLOGY; LEARNING SYSTEMS; PERFORMANCE;

BACKPROPAGATION NEURAL NETWORKS; DYNAMIC PROPERTIES; GENERALIZATION CAPABILITIES; NETWORK SIZE; OVERTRAINING PHENOMENON; TRAINING SET SIZE;

NEURAL NETWORKS;

EID: 0030147563     PISSN: 03784754     EISSN: None     Source Type: Journal    
DOI: 10.1016/0378-4754(95)00003-8     Document Type: Article

References (11)

1. R. Hecht-Nielsen, Theory of the backpropagation neural networks, Proc. Internat. Joint Conf. on Neural Networks, Vol. I (IEEE Press, New York, 1989) pp. 593-611.
2. R. Hecht-Nielsen, Neurocomputing (Addison-Wesley, Reading, MA, 1990).
3. P.J. Werbos, Backpropagation: Past and Future, Proc. Internat. Conf. on Neural Networks, Vol. I (IEEE Press, New York, 1988) pp. 343-353.
4. D.E. Rumelhart, G.E. Hinton and R.J. Williams, Learning internal representations by error propagation, in: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1 (MIT Press, Cambridge, MA, 1989).
5. J.M. McInerney, K.G. Haines, S. Biafore and R. Hecht-Nielsen, Can backpropagation error surfaces have non-global minima?, Manuscript, Dept. El. and Comp. Engrg., University of California at San Diego, August 1988.
6. E.B. Baum, When are k-nearest neighbor and back propagation accurate for feasible sized sets of examples?, in: L.B. Almeida and C.J. Wellekens, eds., Neural Networks, Lecture Notes in Computer Science, Vol. 412, Proc. EURASIP Workshop 1990 (Springer, Berlin, 1990).
7. Y. Chauvin, A backpropagation algorithm with optimal use of the hidden units, in: D. Touretzky, ed., Advances in Neural Information Processing Systems (Morgan-Kaufman, Palo Alto, CA, 1989).
8. Y. Chauvin, Generalization performance of overtrained back propagation networks, in: L.B. Almeida and C.J. Wellekens, eds., Neural Networks, Lecture Notes in Computer Science, Vol. 412, Proc. EURASIP Workshop 1990 (Springer, Berlin, 1990).
9. S.G. Tzafestas and K. Watanabe, Learning algorithms for neural networks with the Kalman filters, J. Intell. and Robotic Systems 3(4) (1990) 305-319.
10. K. Watanabe, K. Shiramizu, T. Fukuda and S.G. Tzafestas, An iterative learning control for noisy systems by using linear neural networks, in: S.G. Tzafestas, ed., Engineering Systems with Intelligence (Kluwer Academic Publishers, Dordrecht, 1991) pp. 205-212.
11. K. Watanabe, T. Fukuda and S.G. Tzafestas, An adaptive control for CARMA systems using linear neural networks, in: P. Borne, S.G. Tzafestas and N.E. Radhy, eds., Mathematics of the Analysis and Design of Process Control (North-Holland, Amsterdam, 1992) pp. 525-534.