论文信息 - A hybrid algorithm for finding the global minimum of error function of neural networks and its applications

A hybrid algorithm for finding the global minimum of error function of neural networks and its applications

Abstract Back propagation has often been applied to adapt artificial neural networks for various pattern classification problems. However, an important limitation of this method is that it sometimes fails to find a global minimum of the total error function of the neural networks. In this article, a hybrid algorithm that combines the modified back-propagation method and the random optimization method is proposed to find the global minimum of the total error function of a neural network in a small number of steps. It is shown that this hybrid algorithm ensures convergence to a global minimum with probability 1 in a compact region of a weight vector space. Further, the results of several computer simulations dealing with the problems of forecasting air pollution density, forecasting stock prices, and determining the octane rating in gasoline blending are given.

[1] Roger J.-B. Wets,et al. Minimization by Random Search Techniques , 1981, Math. Oper. Res..

[2] Scott E. Fahlman,et al. An empirical study of learning speed in back-propagation networks , 1988 .

[3] C. M. Reeves,et al. Function minimization by conjugate gradients , 1964, Comput. J..

[4] S. Geman,et al. Diffusions for global optimizations , 1986 .

[5] N. Baba. A hybrid algorithm for finding a global minimum , 1983 .

[6] Toshio Shoman,et al. A modified convergence theorem for a random optimization method , 1977, Inf. Sci..

[7] C. D. Gelatt,et al. Optimization by Simulated Annealing , 1983, Science.

[8] L. Mark Berliner,et al. Bayesian control in mixture models , 1987 .

[9] V. Cerný. Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm , 1985 .

[10] C. Hwang,et al. Diffusion for global optimization in R n , 1987 .

[11] N. Baba. Convergence of a random optimization method for constrained optimization problems , 1981 .

[12] E. Polak. Introduction to linear and nonlinear programming , 1973 .

[13] Norio Baba,et al. A new approach for finding the global minimum of error function of neural networks , 1989, Neural Networks.

[14] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.