{"references": ["Enrique Castillo. Functional Networks. Neural Processing Letters,\n1998,7:151~159", "Enrique Castillo, Angel Cobo, Jose Manuel Gutierrez. Functional\nNetworks with Applications. Kluwer Academic Publishers, 1999", "Enrique Castillo, Gutierrez JM, Cobo A, Castillo C. A minimax method\nfor learning functional networks. Neural Processing Letters, 2000, 11(1):\n39~49", "Minsky, M, L., & Papert, S.A. Perceptrons. Cambridge, MA: MIT Press,\n1969", "Rumelhart, D.E., Hinton, G.E., & Williams, R.J. Parallel distributed\nprocessing (Vol.1). Cambridge, MA: MIT Press, 1986a.", "James Tin-Yau. Moderating the outputs of support vector machine\nclassifiers. IEEE Transactions On Neural Networks, 1999,10(5):\n1018-1031", "Alfonso Iglesias, Bernardino Arcay, J, M. Cotos, J. A. Taboada, Carlos\nDafonte. A comparison between functional networks and artificial neural\nnetworks for the prediction of fishing catches. Neural comput & applie.\n2004,13:24~31", "Igor T. Podolak. Functional graph model of a neural network. IEEE\nTransactions On System, Man, And Cybernetics-Part B: Cybernetics.\n1998,28(6): 876-881", "Yong-Quan ZHOU. Polynomial Function Recurrent Neural Networks\nModel and Apply. Chinese Journal of Computers, (in Chinese),\n2003,26(9): 1196-1200."]}

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.