NEURAL NETWORK WORLD: A NEURAL NETWORK BASED SELECTION METHOD FOR GENETIC ALGORITHMS

Genetic algorithms (GAs) are stochastic methods that are widely used in search and optimization. The breeding process is the main driving mechanism for GAs that leads the way to find the global optimum. And the initial phase of the breeding process starts with parent selection. The selection utilized in a GA is ef- fective on the convergence speed of the algorithm. A GA can use different selection mechanisms for choosing parents from the population and in many applications the process generally depends on the fitness values of the individuals. Artificial neural networks (ANNs) are used to decide the appropriate parents by the new hybrid algorithm proposed in this study. And the use of neural networks aims to produce better offspring during the GA search. The neural network utilized in this algo- rithm tries to learn the structural patterns and correlations that enable two parents to produce high-fit offspring. In the breeding process, the first parent is selected based on the fitness value as usual. Then it is the neural network that decides the appropriate mate for the first parent chosen. Hence, the selection mechanism is not solely dependent on the fitness values in this study. The algorithm is tested with seven benchmark functions. It is observed from results of these tests that the new selection method leads genetic algorithm to converge faster.

[1]  S. N. Sivanandam,et al.  Introduction to genetic algorithms , 2007 .

[2]  Grace S. Wang,et al.  GA-Based Neural Network to Identification of Nonlinear Structural Systems , 2007, ISNN.

[3]  Akbar A. Javadi,et al.  A hybrid intelligent genetic algorithm , 2005, Adv. Eng. Informatics.

[4]  R. Poli,et al.  Evolving neural networks using a dual representation with a combined crossover operator , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[5]  Yann LeCun,et al.  A theoretical framework for back-propagation , 1988 .

[6]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[7]  Konstantinos P. Ferentinos,et al.  Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms , 2005, Neural Networks.

[8]  K. Matsui.  New selection method to improve the population diversity in genetic algorithms , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[9]  Martin A. Riedmiller,et al.  Rprop - Description and Implementation Details , 1994 .

[10]  Shiu Yin Yuen,et al.  A Genetic Algorithm That Adaptively Mutates and Never Revisits , 2009, IEEE Trans. Evol. Comput..

[11]  S. Y. Yuen,et al.  A Genetic Algorithm That Adaptively Mutates and Never Revisits , 2009, IEEE Transactions on Evolutionary Computation.

[12]  Konstantinos G. Margaritis,et al.  A Proposed Genetic Algorithm Selection Method , 2006 .

[13]  M. Affenzeller,et al.  Offspring Selection: A New Self-Adaptive Selection Scheme for Genetic Algorithms , 2005 .

[14]  Christian Igel,et al.  Improving the Rprop Learning Algorithm , 2000 .

[15]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[16]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[17]  Marcus Hutter,et al.  Fitness uniform selection to preserve genetic diversity , 2001, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[18]  Daniel C. Tse,et al.  Application of Micro Genetic Algorithms and Neural Networks for Airfoil Design Optimization , 2000 .

[19]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[20]  Alberto Taboada-Crispí,et al.  Training of Multilayer Perceptron Neural Networks by Using Cellular Genetic Algorithms , 2006, CIARP.

[21]  Jin Cheng,et al.  Reliability analysis of structures using artificial neural network based genetic algorithms , 2008 .

[22]  Stefan Bornholdt,et al.  General asymmetric neural networks and structure design by genetic algorithms: a learning rule for temporal patterns , 1992, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[23]  C. Fernandes,et al.  A study on non-random mating and varying population size in genetic algorithms using a royal road function , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[24]  Ling Wang,et al.  A hybrid genetic algorithm-neural network strategy for simulation optimization , 2005, Appl. Math. Comput..

[25]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[26]  Kostadin Ivanov,et al.  Sensitivity study on determining an efficient set of fuel assembly parameters in training data for designing of neural networks in hybrid genetic algorithms , 2006 .

[27]  Morteza Ahmadi,et al.  Design of neural networks using genetic algorithm for the permeability estimation of the reservoir , 2007 .

[28]  Kaspar Althoefer,et al.  Neural Network World , 2000 .

[29]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[30]  D. E. Goldberg,et al.  Genetic Algorithms in Search, Optimization & Machine Learning , 1989 .

[31]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.