Application of Functional Network to Solving Classification Problems

In this paper two models using a functional network were employed to solving classification problem. Functional networks are generalized neural networks, which permit the specification of their initial topology using knowledge about the problem at hand. In this case, and after analyzing the available data and their relations, we systematically discuss a numerical analysis method used for functional network, and apply two functional network models to solving XOR problem. The XOR problem that cannot be solved with two-layered neural network can be solved by two-layered functional network, which reveals a potent computational power of functional networks, and the performance of the proposed model was validated using classification problems.

Authors:

• Yong-Quan Zhou
• Deng-Xu He
• Zheng Nong

Keywords:

• Functional network
• neural network
• XOR problem
• classification
• numerical analysis method.

References:

[1] Enrique Castillo. Functional Networks. Neural Processing Letters,
1998,7:151~159
[2] Enrique Castillo, Angel Cobo, Jose Manuel Gutierrez. Functional
Networks with Applications. Kluwer Academic Publishers, 1999
[3] Enrique Castillo, Gutierrez JM, Cobo A, Castillo C. A minimax method
for learning functional networks. Neural Processing Letters, 2000, 11(1):
39~49
[4] Minsky, M, L., & Papert, S.A. Perceptrons. Cambridge, MA: MIT Press,
1969
[5] Rumelhart, D.E., Hinton, G.E., & Williams, R.J. Parallel distributed
processing (Vol.1). Cambridge, MA: MIT Press, 1986a.
[6] James Tin-Yau. Moderating the outputs of support vector machine
classifiers. IEEE Transactions On Neural Networks, 1999,10(5):
1018-1031
[7] Alfonso Iglesias, Bernardino Arcay, J, M. Cotos, J. A. Taboada, Carlos
Dafonte. A comparison between functional networks and artificial neural
networks for the prediction of fishing catches. Neural comput & applie.
2004,13:24~31
[8] Igor T. Podolak. Functional graph model of a neural network. IEEE
Transactions On System, Man, And Cybernetics-Part B: Cybernetics.
1998,28(6): 876-881
[9] Yong-Quan ZHOU. Polynomial Function Recurrent Neural Networks
Model and Apply. Chinese Journal of Computers, (in Chinese),
2003,26(9): 1196-1200.