Abstract
Error back-propagation algorithm of the multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the fuzzy multilayer perceptron which is composed of the ART1 and the fuzzy neural network. The proposed fuzzy multilayer perceptron using the self-generation method applies not only the ART1 to create the nodes from the input layer to the hidden layer, but also the winner-take-all method, modifying stored patterns according to specific patterns, to adjustment of weights. The proposed learning method was applied to recognize individual numbers of student identification cards. Our experimental result showed that the possibility of local-minima was decreased and the learning speed and the paralysis were improved more than the conventional error back-propagation algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
James, A., Freeman, A.: Neural Networks: Algorithm, Application and Programming Techniques. Addison-Wesley, Reading (1991)
Hirose, Y., Yamashita, K., Hijiya, S.: Back-Propagation Algorithm Which Varies the Number of Hidden Units. Neural Networks 4, 61–66 (1991)
Kavuri, S.N., Ventatasubramanian, V.: Solving the Hidden Node Problem in Neural Networks with Ellipsoidal Units and Related Issues. In: Proceedings of IJCNN, vol. 1, pp. 775–780 (1992)
Kim, K.B., Kang, M.H., Cha, E.Y.: A Fuzzy Self-Organized Backpropagation using Nervous System. In: Proceeding of SMC, vol. 2, pp. 1457–1462 (1997)
Kim, K.B., Kim, Y.J.: Recognition of English Calling Cards by Using Enhanced Fuzzy Radial Basis Function Neural Networks. IEICE Trans. Fundamentals E87-A(6), 1355–1362 (2004)
Gupta, M.M., Qi, J.: On Fuzzy Neuron Models. In: Proceedings of IJCNN, vol. 2, pp. 431–435 (1991)
Saito, T., Mukaidono, M.: A Learning algorithm for Max-Min Network and its Application to Solve Relation Equations. In: Proceedings of IFSA, pp. 184–187 (1991)
Czogala, E., Buckley, J.J.: Fuuzy Neural Controller. In: Proceedings of IEEE Fuzzy Systems, vol. 1, pp. 197–202 (1992)
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
Kim, K.B., Park, C.S. (2004). An Enhanced Fuzzy Multilayer Perceptron. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_151
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_151
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive