A conjugate gradient based method for Decision Neural Network training

Subject Areas : Statistics

M.  Nadershahi ¹ (PhD. student, Department of Industrial engineering, Payame Noor University, Tehran, Iran.)
A. D.  Safi Samghabadi ² (Industrial Engineering Department , Faculty of Engineering, Payame Noor University, Tehran, Iran)
R.  Tavakkoli-Moghaddam ³ (Professor, Faculty of Industrial engineering, Tehran University, Tehran, Iran.)

Received: 2018-03-28 Accepted : 2018-09-18 Published : 2019-02-20

Keywords: آموزش شبکه عصبی تصمیم, روش گرادیان مزدوج, مسائل تصمیم‌گیری چندهدفه, تخمین تابع مطلوبیت,

Abstract :

Decision Neural Network is a new approach for solving multi-objective decision-making problems based on artificial neural networks. Using inaccurate evaluation data, network training has improved and the number of educational data sets has decreased. The available training method is based on the gradient decent method (BP). One of its limitations is related to its convergence speed. Therefore, decision makers can simply guess the necessary data. In this paper, for increasing the Decision Neural Network training efficiency, a conjugate gradient based method has developed for network training. The key point in decision neural network training is to keep the same structures and parameters of the two sub network (multilayer perceptron) through training process. The efficiency of the proposed method is evaluated by estimating linear and nonlinear utility function of multi-objective decision problems. The results of the proposed method are compared with previous existing method and show that in the proposed method, convergence is faster than previous methods and the results are more favorable.

References:

مراجع

[1]     Chen, J. & Lin, S, A Neural Network Approach- Decision Neural Network (DNN) for preference assessment, IEEE Trans. Syst. Man, Cyber net,  2004, vol 34, No. 2, pp.219-225.

[2]     Wang, J., & Malakooti, B., A feed forward neural network for multiple criteria decision making, Computer. Oper. Res, 1992, Vol. 19, No. 2, pp. 151-167.

[3]     Keeney, R. L., Raffia, H, Decisions with multiple objectives. Cambridge Univ. Press, U.K., 1993.

[4]      Bell, D. E., Consistent assessment procedures using conditional utility functions. Oper. Res, 1979, vol 27.PP. 1054-1066.

[5]     Dyer, J. S., & Sarin, R. K., “Measurable multi attribute value functions”, Ops Res , 1979, vol. 27, PP. 810-822.

[6]      Farquhar, P. H., “A fractional hypercube decomposition theorem for multi attribute utility functions”, Ops Res.  1975, Vol.. 23, pp. 941-967.

[7]      Fishburn, P. G., “von Neumann Morgenstern utility functions on two attributes”, Ops Res , 1974, Vol. 22, pp. 35-45.

[8]     Kirkwood, C. W., “Parametrically dependent preferences for multi attributed consequences”, Ops Res, 1976, Vol. 24, pp. 92-103.

[9]      Benayoun,R, de Montgolfier,J, Tergny,J and Laritchev,O,I, Linear programming with multiple objective functions: Step method (STEM), Math. Program., 1971, vol. 1, pp. 366–387.

[10] Geoffrion, M,   Dyer, J, S and A. Feinberg, An interactive approach for multi-criterion optimization, with an application to the operation of an academic department, Manage. Sci., 1972, vol. 19, no. 4, pp. 357–368.

[11]  Gardiner,L , R  and  Steuer, R , E, Unified interactive multiple objective programming, Eur. J. Oper. Res., 1994, vol. 74, pp. 391–406.

[12]  Sun, M, Stam, A, Steuer, R. E., Interactive multiple objective programming problems using Tchebycheff programs and artificial neural networks. Computer & Oper. Res, 2000, 27, PP.601-620.

[13]  Sun, M, Stam, A , Steuer, R. E., “Solving multiple objective programming problems  using feed-forward artificial neural networks: The interactive FFANN procedure,” Manage. Sci , 1996, vol. 42, No .6, pp. 835–849.

[14] Malakooti, B and Zhou, Y, Feed-forward artificial neural networks for solving discrete multiple criteria decision making problems, Manage.Sci., , 1994, vol. 40, No. 11, pp. 1542–1560.

[15] R. Hecht-Nielsen, “Theory of the backpropagation neural networks,” in Proc. Int. Joint Conf. Neural Networks, 1989و pp. 593–611.

[16]  Shih, H.S., Wen, U.P.,  Lee, E.S.,  Lan, K.M.,  Hsiao, H.C., A neural network   approach to multi objective and multilevel programming problems, comput &  math, 2004, vol. 48, pp. 95-108.

[17]  Huang, H.Z, Tian, Z, J. ZUO, M, Intelligent interactive multi objective optimization method and its application to reliability optimization, IIE Transactions 2005, 37, 983–993.

[18] Gen, M, Ida, K. and Kobuchi, R, Neural network technique for fuzzy multiobjective linear   programming, computer and industrial engineering”, 1998, vol 35, NO. 3, PP. 543-546.

[19]  Golmohammadi, D, Neural network application for fuzzy multi-criteria decision making problems, Int. J. production Economics131, 2011, pp. 490–504.

[20] Golmohammadi, D, A neural network decision-making model for job-shop scheduling, International Journal of Product Res, 2013, Vol. 51, No. 17, pp. 5142–5157.

[21] Chen, J. & Lin, S., “An interactive neural network-based approach for solving multiple criteria decision-making problems”, Decision support systems, 2003, vol. 36, pp. 137-146.

[22] Gal, T., “Nonessential objective within network approaches for MCDM”, European Journal of Operation Research, 2006, vol. 168, pp. 584-592.

[23]  Singh, R.K., Choudhury, A.K., Tiwari, M.K., Shankar, R, “Improved Decision Neural Network IDNN) based consensus method to solve a multi-objective group decision making problem”, Advanced Engineering Informatics, 2007, vol 21, pp. 335-348.