A novel optimization method named RasID-GA (an abbreviation of Adaptive Random Search with Intensification and Diversification combined with Genetic Algorithm) is proposed in order to enhance the searching ability of conventional RasID, which is a kind of Random Search with Intensification and Diversification. In this paper, the timing of switching from RasID to GA, or from GA to RasID is also studied. RasID-GA is compared with parallel RasIDs and GA using 23 different objective functions, and it turns out that RasID-GA performs well compared with other methods.

In general, neural networks are widely used in pattern recognition, system modeling and prediction, and can model complex nonlinear systems. In the previous work, we proposed a novel training algorithm, Adaptive Random Search with Intensification and Diversification combined with Genetic Algorithm (RasID‐GA), for training the multibranch recurrent neural networks recently developed. In this paper, RasID‐GA has been applied to predict stock market prices using the multibranch feed forward neural networks. We predicted the next day's closing stock price with several past closing stock prices. We used the stock prices of 20 brands for 720 days in order to evaluate the generalization ability of the proposed method. Copyright © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

This paper applies a Adaptive Random search with Intensification and Diversification combined with Genetic Algorithm (RasID-GA) to neural network training. In the previous work, we proposed RasID-GA which combines the best properties of RasID and Genetic Algorithm for optimization. Neural networks are widely used in pattern recognition, system modeling, prediction and other areas. Although most neural network training uses gradient based schemes such as wellknown back-propagation (BP), but sometimes BP is easily dropped into local minima. In this paper, we train multi-branch neural networks using RasID-GA with constraint coefficient C by which the feasible solution space is controlled. In addition, we use Mackey-Glass time prediction to test a generalization ability of the proposed method.

Constrained optimization problems have been handled in the field of applied mathematics. On the other hand, evolutionary computations, a kind of computationally intensive methods are now applied to many applications. This paper presents RasID-GA (an abbreviation of Adaptive Random Search with Intensification and Diversification combined with Genetic Algorithm) for constrained optimization problems. The conventional constrained optimization methods use penalty functions to solve given problems. But, it is generally said that the penalty function is have to handle. In the proposed method, parallel RasIDs are combined with GA, and can find the optimal solution of constrained problems efficiently and effectively without using penalty functions.

This paper applies an Adaptive Random search with Intensification and Diversification combined with Genetic Algorithm (RasID-GA) to neural network training. In the previous work, we proposed RasID-GA which combines the best properties of RasID and Genetic Algorithm for optimization. Neural networks are widely used in pattern recognition, system modeling, prediction and other areas. Although most neural network training uses gradient based schemes such as well-known back-propagation (BP), but sometimes BP is easily dropped into local minima. In this paper, we train newly developed multi-branch neural networks using RasID-GA with constraint coefficientCby which the feasible solution space is controlled. In addition, we use Mackey-Glass time prediction to test a generalization ability of the proposed method.