^{}Department of Mathematics, Firoozkooh Branch, Islamic Azad Uni- versity, Firoozkooh, Iran

Abstract

In this paper, a novel hybrid method based on learning algorithm of fuzzy neural network and Newton-Cotes methods with positive coefficient for the solution of linear Fredholm integro-differential equation of the second kind with fuzzy initial value is presented. Here neural network is considered as a part of large field called neural computing or soft computing. We propose a learning algorithm from the cost function for adjusting fuzzy weights. This paper is one of the first attempts to derive learning algorithms from fuzzy neural networks with real input, fuzzy output, and fuzzy weights. Finally, we illustrate our approach by numerical examples.

bibitem{aba} S. Abbasbandy, E. Babolian and M. Alavi, {it Numerical method for solving linear fredholm fuzzy integral equations of the second kind}, Chaos Solitons & Fractals, {bf 31} (2007), 138-146.

bibitem{abo} S. Abbasbandy and M. Otadi, {it Numerical solution of fuzzy polynomials by fuzzy neural network}, Applied Mathematics and Computation, {bf 181} (2006), 1084-1089.

bibitem{abom} S. Abbasbandy, M. Otadi and M. Mosleh, {it Numerical solution of a system of fuzzy polynomials by fuzzy neural network}, Information Sciences, {bf 178} (2008), 1948-1960.

bibitem{al1} G. Alefeld and J. Herzberger, {it Introduction to interval computations}, Academic Press, New York, 1983.

bibitem{aaa1} T. Allahviranloo, E. Ahmady and N. Ahmady, {it Nth-order fuzzy linear differential eqations},Information Sciences, {bf 178} (2008), 1309-1324.

bibitem{aaa2} T. Allahviranloo, N. Ahmady and E. Ahmady, {it Numerical solution of fuzzy differential eqations by predictor-corrector method}, Information Sciences, {bf 177} (2007), 1633-1647.

bibitem{at} K. E. Atkinson, {it An introduction to numerical analysis}, New York, Wiley, 1987.

bibitem{bsa} E. Babolian, H. S. Goghary and S. Abbasbandy, {it Numerical solution of linear fredholm fuzzy integral equations of the second kind by adomian method}, Applied Mathematics and Computation, {bf 161} (2005), 733-744.

bibitem{bm} P. Balasubramaniam and S. Muralisankar, {it Existence and uniqueness of fuzzy solution for the nonlinear fuzzy integro-differential equations}, Applied mathematics letters, {bf 14} (2001), 455-462.

bibitem{bb} B. Bede, I. J. Rudas and A. L. Bencsik, {it First order linear fuzzy differential eqations under generalized differentiability}, Information Sciences, {bf 177} (2007), 1648-1662.

bibitem{ber} J. F. Bernard, {it Use of rule-based system for process control}, IEEE Control System Management, {bf 8} (1988), 3-13.

bibitem{bf} J. J. Buckley and T. Feuring, {it Fuzzy differential equations}, Fuzzy Sets and Systems, {bf 110} (2000), 69-77.

bibitem{by} J. J. Buckley and Y. Hayashi, {it Can fuzzy neural nets approximate continuous fuzzy functions?}, Fuzzy Sets and Systems, {bf 61} (1994), 43-51.

bibitem{cz} S. L. Chang and L. A. Zadeh, {it On fuzzy mapping and control}, IEEE Transactions Systems Man and Cybernetics, {bf 2} (1972), 30-34.

bibitem{che} Y. C. Chen and C. C. Teng, {it A model reference control structure using a fuzzy neural network}, Fuzzy Sets and Systems, {bf 73} (1995), 291-312.

bibitem{com} W. Congxin and M. Ming, {it On embedding problem of fuzzy number space}, Fuzzy Sets and Systems, {bf 44} (1991), 33-38.

bibitem{dd} D. Dubois and H. Prade, {it Operations on fuzzy numbers}, International Journal of Systems Science, {bf 9} (1978), 613-626.

bibitem{dp} D. Dubois and H. Prade, {it Towards fuzzy differential calculus}, Fuzzy Sets and Systems, {bf 8} (1982), 225-233.

bibitem{effati} S. Effati and M. Pakdaman, {it Artificial neural network approach for solving fuzzy differential equations}, Information Sciences, {bf 180} (2010), 1434-1457.

bibitem{wf} W. Fei, {it Existence and uniqueness of solution for fuzzy random differential equations with non-lipschitz coefficients}, Information Sciences, {bf 177} (2007), 4329-4337.

bibitem{fmk} M. Friedman, M. Ma and A. Kandel, {it Numerical solutions of fuzzy differential and integral equations}, Fuzzy Sets and Systems, {bf 106} (1999), 35-48.

bibitem{gv} R. Goetschel and W. Voxman, {it Elementary fuzzy calculus}, Fuzzy Sets and Systems, {bf 18} (1986), 31-43.

bibitem{go} D. Gottlieb and S.A. Orszag, {it Numerical analysis of spectral methods}, Theory and applications, CBMS-NSF Regional Conference Series in Applied Mathematics, SIAM, Philadelphia, {bf 26} (1977). bibitem{hdb} M. T. Hagan, H. B. Demuth and M. Beale, {it Neural network design}, PWS publishing company, Massachusetts, 1996.

bibitem{jb2} Y. Hayashi, J. J. Buckley and E. Czogala, {it Fuzzy neural network with fuzzy signals and weights}, International Journal of Intelligent Systems, {bf 8} (1993), 527-537.

bibitem{ha} S. Haykin,{it Neural networks: a comprehensive foundation}, Prentice Hall, New Jersey, 1999.

bibitem{h} H. Hochstadt, {it Integral equations}, New York: Wiley, 1973.

bibitem{hsw} K. Hornick, M. Stinchcombe and H. White, {it Multilayer feedforward networks are universal approximators}, Neural Networks, {bf 2} (1989), 359-366.

bibitem{dr} H. Ishibuchi, K. Kwon and H. Tanaka, {it A learning algorithm of fuzzy neural networks with triangular fuzzy weights}, Fuzzy Sets and Systems, {bf 71} (1995), 277-293.

bibitem{imt} H. Ishibuchi, K. Morioka and I.B. Turksen, {it Learning by fuzzified neural networks}, International Journal of Approximate Reasoning, {bf 13} (1995), 327-358.

bibitem{ism} H. Ishibuchi and M. Nii, {it Numerical analysis of the learning of fuzzified neural networks from fuzzy if-then rules}, Fuzzy Sets and Systems, {bf 120} (2001), 281-307.

bibitem{wc1} H. Ishibuchi, H. Okada and H. Tanaka, {it Fuzzy neural networks with fuzzy weights and fuzzy biases}, Proceedings ICNN, {bf 93} (1993), 1650-1655.

bibitem{ito} H. Ishibuchi, H. Tanaka and H. Okada, {it Fuzzy neural networks with fuzzy weights and fuzzy biases}, IEEE International Conferences on Neural Networks, (1993), 1650-1655.

bibitem{kal} O. Kaleva, {it Fuzzy differential equations}, Fuzzy Sets and Systems, {bf 24} (1987), 301-317.

bibitem{kh} T. Khanna, {it Foundations of neural networks}, Addison-Wesly, Reading, MA, 1990.

bibitem{kcy} G. J. Klir, U. S. Clair, B. Yuan, {it Fuzzy set theory: foundations and applications}, Prentice-Hall, 1997.

bibitem{kbrh} P. V. Krishnamraju, J. J. Buckley, K. D. Relly and Y. Hayashi, {it Genetic learning algorithms for fuzzy neural nets}, IEEE International Conference on Fuzzy Systems, (1994), 1969-1974.

bibitem{lag} I. E. Lagaris and A. Likas, {it Artificial neural networks for solving ordinary and partial differential equations}, IEEE Transactions on Neural Networks, September, {bf 9}textbf{(5)} (1998).

bibitem{lam} J. D. Lamber, {it Computational methods in ordinary differential equations}, John Wiley & Sons, New York, 1983.

bibitem{lf} A. Lapedes and R. Farber, {it How neural nets work?}, Neural Information Processing Systems, AIP, 1988, 442-456. bibitem{lk} H. Lee and I. S. Kang, {it Neural algorithms for solving differential equations}, Journal of Computational Physics, {bf 91} (1990), 110-131.

bibitem{tlee} T. Leephakpreeda, {it Novel determination of differential-equation solutions: universal approximation method}, Computational and Applied Mathematics, {bf 146} (2002), 443-457.

bibitem{leng} G. Leng, G. Prasad and T. M. McGinnity, {it An on-line algorithm for creating self-organizing fuzzy neural networks}, Neural Networks, {bf 17} (2004), 1477-1493.

bibitem{lin1} D. Lin and X. Wang, {it Observer-based decentralized fuzzy neural sliding mode control for interconnected unknown chaotic systems via network structure adaptation}, Fuzzy Sets and Systems, {bf 161} (2010), 2066-2080.

bibitem{lin3} D. Lin and X. Wang, {it Self-organizing adaptive fuzzy neural control for the synchronization of uncertain chaotic systems with random-varying parameters}, Neurocomputing, {bf 74} (2011), 2241-2249.

bibitem{lin2} D. Lin, X. Wang, F. Nian and Y. Zhang, {it Dynamic fuzzy neural networks modeling and adaptive backstepping tracking control of uncertain chaotic systems}, Neurocomputing, {bf 73} (2010), 2873-2881.

bibitem{li} R. P. Lippmann, {it An introduction to computing with neural nets}, IEEE ASSP Magazine, (1987), 4-22.

bibitem{mas} A. Malek and R. Shekari Beidokhti, {it Numerical solution for high order differential equations using a hybrid neural network-Optimization method}, Applied Mathematics and Computation, {bf 183} (2006), 260-271.

bibitem{mf} A. J. Meade Jr and A. A. Fernandez, {it The numerical solution of linear ordinary differential equations by feedforward neural networks}, Mathematical and Computer Modelling, {bf 19}textbf{(12)} (1994), 1-25.

bibitem{mef} A. J. Meade Jr and A. A. Fernandez, {it Solution of nonlinear ordinary differential equations by feedforward neural networks}, Mathematical and Computer Modelling, {bf 20}textbf{(9)} (1994), 19-44.

bibitem{mbcrb} M. T. Mizukoshi, L. C. Barros, Y. Chalco-Cano, H. Román-Flores and R. C. Bassanezi, {it Fuzzy differential equations and the extention principle}, Information Sciences, {bf 177} (2007), 3627-3635.

bibitem{mto} M. Mosleh, T. Allahviranloo and M. Otadi, {it Evaluation of fully fuzzy regression models by fuzzy neural network}, Neural Comput and Applications, {bf 21} (2012), 105 - 112.

bibitem{mom1} M. Mosleh and M. Otadi, {it Minimal solution of fuzzy linear system of differential equations}, Neural Comput and Applications, {bf 21} (2012), 329-336.

bibitem{mom} M. Mosleh and M. Otadi, {it Simulation and evaluation of fuzzy differential equations by fuzzy neural network}, Applied Soft Computing, {bf 12} (2012), 2817–2827.

bibitem{moa1} M. Mosleh, M. Otadi and S. Abbasbandy, {it Evaluation of fuzzy regression models by fuzzy neural network}, Journal of Computational and Applied Mathematics, {bf 234} (2010), 825-834. bibitem{moa2} M. Mosleh, M. Otadi and S. Abbasbandy, {it Fuzzy polynomial regression with fuzzy neural networks}, Applied Mathematical Modelling, {bf 35} (2011), 5400-5412.

bibitem{oma1} M. Otadi and M. Mosleh, {it Simulation and evaluation of dual fully fuzzy linear systems by fuzzy neural network}, Applied Mathematical Modelling, {bf 35} (2011), 5026-5039.

bibitem{oma2} M. Otadi, M. Mosleh and S. Abbasbandy, {it Numerical solution of fully fuzzy linear systems by fuzzy neural network}, Soft Computing, {bf 15} (2011), 1513-1522.

bibitem{oms} M. Otadi, M. Mosleh, S. Saidanlu and N. A. Aris, {it Fuzzy hyperbolic regression with fuzzy neural networks}, Australian Journal of Basic and Applied Sciences, {bf 5}textbf{(10)} (2011), 838-847.

bibitem{pse} G. Papaschinopoulos, G. Stefanidou and P. Efraimidis, {it Existence, uniquencess and asymptotic behavior of the solutions of a fuzzy differential equation with piecewise constant argument}, Information Sciences, {bf 177} (2007), 3855-3870.

bibitem{pi} P. Picton, {it Neural Networks}, Second edition, Palgrave, Great Britain, 2000.

bibitem{pr} M. L. Puri and D. Ralescu, {it Fuzzy random variables}, Journal of Mathematical Analysis and Applications, {bf 114} (1986), 409-422.

bibitem{rrl} R. Rodriguez-Lopez, {it Comparison results for fuzzy differential eqations}, Information Sciences, {bf 178} (2008), 1756-1779.

bibitem{ru} D. E. Rumelhart and J. L. McClelland, {it Parallel distributed processing}, MIT Press, Cambridge, MA, 1986.

bibitem{sc} R. J. Schalkoff, {it Artificial neural networks}, McGraw-Hill, New York, 1997.

bibitem{seik} S. Seikkala, {it On the fuzzy initial value problem}, Fuzzy Sets and Systems, {bf 24} (1987), 319-330.

bibitem{st} J. Stanley, {it Introduction to neural networks}, Sierra Mardre, 1990.

bibitem{sb} J. Store and R. Bulirsch, {it Introduction to numerical analysis}, Springer-Verlag, New York, 1993.

bibitem{tung} W. L. Tung and C. Quek, {it A generic self-organizing fuzzy neural network}, IEEE Transactions on Neural networks, {bf 13} (2002), 1075-1086.

bibitem{yuan} X. Wang and J. Zhao, {it Cryptanalysis on a parallel keyed hash function based on chaotic neural network}, Neurocomputing, {bf 73} (2010,) 3224-3228.

bibitem{xin} W. Xingyuan, X. Bing and Z. Huaguang, {it A multi-ary number communication system based on hyperchaotic system of 6th-order cellular neural network}, Communications in Nonlinear Science and Numerical Simulation, {bf 15} (2010), 124-133.

bibitem{kin} L. A. Zadeh, {it The concept of a liguistic variable and its application to approximate reasoning} Information Sciences, {bf 8} (1975), 199-249, 301-357; {bf 9} (1975), 43-80.

bibitem{laz} L. A. Zadeh, {it Is there a need for fuzzy logic?}, Information Sciences, {bf 178} (2008), 2751-2779.

bibitem{zhang1} H. G. Zhang and D. R. Liu, {it Fuzzy modeling and fuzzy control}, Boston, 2006.

bibitem{zhang2} H. G. Zhang and Y. B. Quan, {it Modeling, identification and control of a class of nonlinear systems}, IEEE Transactions on Fuzzy Systems, {bf 9} (2001), 349-354.