Abstract
BP algorithm is frequently applied to train feedforward neural network, but it often suffers from slowness of convergence speed. In this paper, an efficient learning algorithm and its improved algorithm based on local search are proposed. Computer simulations with standard problems such as XOR, Parity, TwoNorm and MushRoom problems are presented and compared with BP algorithm. Experimental results indicate that our proposed algorithms achieve accuracy much better than BP algorithm and convergence speed much faster than BP algorithm, and the generalization of our proposed algorithms for TwoNorm and MushRoom problems is comparable to BP algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
McClulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in neurons activity. Bulletin of mathematical biophysics 5, 115–133 (1943)
Judd, J.S.: Neural Network Design and Complexity of Learning. MIT Press, Cambridge (1990)
Blum: Training A 3-Node Neural Network Is NP-Complete (1992)
Sosic, R., Gu, J.: A polynomial time algorithm for the n-queens problem. SIGART Bulletin 1, 7–11 (1990)
Sosic, R., Gu, J.: Fast search algorithms for n-queens problem. IEEE Trans. System, Man and Cybernetics 6, 1572–1576 (1991)
Sosic, R., Gu, J.: Efficient Local Search With Conflict Minimization: A Case Study of the n-Queens Problem. IEEE Trans. System, Man and Cybernetics 6, 661–668 (1994)
Gu, J., Huang, X.: Efficient Local Search With Search Space Smoothing: A Case Study of Traveling Salesman Problem (TSP). IEEE Trans. System, Man and Cybernetics 24, 728–735 (1994)
Gu, J.: Local Search for Satisfiability (SAT) Problem. IEEE Trans. System, Man and Cybernetics 23, 1108–1129 (1993)
Selman, B., Levesque, H., Mitchell, D.: A New Method for Solving Hard Satisfiability Problems. In: Proceedings of the Tenth National Conference on Artificial Intelligence, pp. 440–446 (1992)
Chan, L.W., Fallside, F.: An adaptive training algorithm for backpropagation networks. Computer Speech and Language 2, 205–218 (1987)
Salomon: Ralf Adaptive Regelung der Lernrate bei back-propagation. Forschungsberichte des Fachbereichs Informatik. Technische Universitat Berlin, Bericht (1989)
Silva, F.M., Almeida, L.B.: Almeida. Speeding up Backpropagation. In: Eckmiller, R. (ed.) Advanced Neural Computers, pp. 151–158 (1990)
Moller, M.F.: A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks 6, 525–633 (1993)
Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Network 5, 989–993 (1994)
Engel, J.: Teaching feed-forward neural networks by simulated annealing. Complex Systems 2, 641–648 (1988)
Prados, D.L.: New learning algorithm for training multilayer neural networks that uses genetic-algorithm techniques. Electronics Letters 28, 1560–1561 (1992)
Montana, D.J.: Neural network weight selection using genetic algorithms. Intelligent Hybrid Systems, pp. 85–104. Wiley, New York (1995)
Pandya, A.S., Sazbo, R.: A Fast Learning Algorithm for Neural Network Applications. IEEE, 1569–1573 (1991)
Venugopal, K.P., Pandya, A.S.: Alopex Algorithm For Training Multilayer Neural Networks. IEEE, 196–201
Unnikrishnan, K.P., Venugopal, K.P.: Alopex: a correlation-based learning algorithm for feedforward and recurrent neural networks. Neural Computations 6, 469–490 (1994)
Breiman, L.: Bias, variance and arcing classifiers. Tec. Report 460, Statistics department. University of California (1996)
Merz, C.J., Murphy, P.: UCI repository of machine learning database., http://www.ics.uci.edu/~mlearn/MLRepository.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tan, S., Gu, J. (2004). An Efficient Learning Algorithm for Feedforward Neural Network. In: Lemaître, C., Reyes, C.A., González, J.A. (eds) Advances in Artificial Intelligence – IBERAMIA 2004. IBERAMIA 2004. Lecture Notes in Computer Science(), vol 3315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30498-2_77
Download citation
DOI: https://doi.org/10.1007/978-3-540-30498-2_77
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23806-5
Online ISBN: 978-3-540-30498-2
eBook Packages: Springer Book Archive