Skip to main content
No Access

Generation of neural networks using a genetic algorithm approach

Published Online:pp 289-302https://doi.org/10.1504/IJBIC.2013.057183

This paper discusses the generation of neural networks that are obtained from the evolution of individual’s population in a genetic algorithm. For achieving this, the population of individuals for the genetic algorithm is formed of structural elements which constitute the neural networks. These elements include the number of layers, neurons per layer, transfer functions and the connections between neurons in the network, among others. These individuals as can be seen a structure which has the ability to evolve rather than a standard genotype. Furthermore, the size of the individuals is not defined and depends mainly on the neural network which in turn depends on the problem to be solved. This structure considered as an evolutionary entity, is able to evolve until convergence towards a suitable structure is achieved. The fitness function is specified with the features of the problem to be solved by the neural network. This algorithm has been tested successfully in solving classification problems, as in the case of alpha-numerical character recognition, and has been compared against a neural network obtained by conventional means. Better results were obtained with the neural network generated by using genetic programming of this type of evolutionary entities.

Keywords

neural networks, evolutionary algorithm, evolutionary entity, genetic algorithms

References

  • 1. Aliev, R.A. , Fazlollahi, B. , Vahidov, R.M. (2001). ‘Genetic algorithm-based learning of fuzzy neural networks. Part 1: feed-forward fuzzy neural networks’. Fuzzy Sets and Systems. 118, 2, Elsevier, 351-358 Google Scholar
  • 2. Alvarez, G. Can We Make Genetic Algorithms Work in High-dimensionality Problems?, Stanford Exploration Project. 2002, 09, 27, 195-212, Report SEP 112 Google Scholar
  • 3. Arbib, M.A. (2003). The Handbook of Brain Theory and Neural Networks. 2nd ed., Cambridge, MA, USA:The MIT Press , ISBN: 0-262¬01197-2 Google Scholar
  • 4. Ayala-Ramirez, V. , Garcia-Capulin, C.H. , Perez-Garcia, A. , Sanchéz-Yanez, R.E. (2006). ‘Circle detection on images using genetic algorithms’. Pattern Recognition Letters. 27, 6, Elsevier, 652-657 Google Scholar
  • 5. Beale, M.H. , Hagan, M.T. , Demuth, H.B. MATLAB Neural Network Toolbox™, User’s Guide, Version 7.0.3, Release 2012a. 2012, 03, Natick, MA, USA:The MathWorks, Inc. Google Scholar
  • 6. Cantu-Paz, E. (2001). Efficient and Accurate Parallel Genetic Algorithms. Norwel, MA, USA:Kluwer Academic Publishers , ISBN-10: 0-7923-7221-2 Google Scholar
  • 7. Chen, M. , Yao, Z. (2008). ‘Classification techniques of neural networks using improved genetic algorithms’. Second International Conference on Genetic and Evolutionary Computing (WGEC ‘08), IEEE Computer Society Google Scholar
  • 8. Coello Coello, C.A. , Lamont, G.B. , Van Veldhuizen, D.A. (2007). Evolutionary Algorithms for Solving Multi-Objective Problems. New York, NY, USA:Springer , ISBN 978-0-387-33254-3 Google Scholar
  • 9. De La Cruz, C. , Bastos-Filho, T. , Patino, H.D. , Carelli, R. (2009). ‘Evolving hardware using a new evolutionary algorithm based on evolution of a species’. Int. J. of Bio-Inspired Computation. 1, 3, 164-176 AbstractGoogle Scholar
  • 10. Fernandes, C.M. , Laredo, J.L.J. , Mora, A.M. , Rosa, A.C. , Merelo, J.J. (2011). ‘A study on the mutation rates of a genetic algorithm interacting with a Sandpile’. Applications of Evolutionary Computation, Lecture Notes in Computer Science. 6624, 32-42, Part I Google Scholar
  • 11. Gaxiola, F. , Melin, P. , Valdez, F. , Castillo, O. (2011). ‘Modular neural networks with Type-2 fuzzy integration for pattern recognition of iris biometric measure’. 7095, MICAI, 2, 363-373 Google Scholar
  • 12. Goldberg, D.E. Genetic Algorithms in Search, Optimization and Machine Learning. 1989, 01, Boston, MA, USA:Addison Wesley Publishing Company , ISBN:0201157675 Google Scholar
  • 13. Hagan, M.T. , Demuth, H.B. , Beale, M.H. (1995). Neural Network Design. Boston, MA, USA:PWS Pub. Co. , ISBN: 0-9717321-0-8 Google Scholar
  • 14. Harding, S. , Banzhaf, W. , Miller, J.F. (2011). ‘A survey of self modifying Cartesian genetic programming’. Genetic Programming Theory and Practice VIII. 8, 1, 91-107, ISBN-13: 978-1-4419-7746-5 Google Scholar
  • 15. Haykin, S. (1998). Neural Networks: A Comprehensive Foundation. 2nd ed., Upper Saddle River, NJ, USA:Prentice Hall , ISBN-10: 0132733501 Google Scholar
  • 16. Icke, I. , Rosenberg, A. (2011). ‘Multi-objective genetic programming for visual analytics’. Genetic Programming. 6621, 1, Heidelberg, Germany:Springer , 322-334, ISBN-13: 978-3-642-20406-7 Google Scholar
  • 17. Janglová, D. (2004). ‘Neural networks in mobile robot motion’. International Journal of Advanced Robotic Systems. 1, 1, 15-22, ISSN: 1729-8806 Google Scholar
  • 18. Koza, J.R. (1998). Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA, USA:The MIT Press , ISBN-10: 0-262-11170-5 Google Scholar
  • 19. Kulkarni, A.D. Computer Vision and Fuzzy-Neural Systems. 2001, 05, 08, 1st ed., Upper Saddle River, NJ, USA:Prentice Hall , ISBN-10: 0-13-570599-1 Google Scholar
  • 20. Luis-Perez, F.E. , Trujillo-Romero, F. , Martinez-Velazco, W. (2011). ‘Control of a service robot using the Mexican sign language’. 7095, MICAI, 2, 419-430 Google Scholar
  • 21. Maung, T.H.H. ‘Real-time hand tracking and gesture recognition system using neural networks’. World Academy of Science, Engineering and Technology. 2009, 02, 26, 466-470 Google Scholar
  • 22. Michalewicz, Z. (1998). Genetic Algorithms + Data Structures = Evolution Programs. 3rd Revised and Extended Edition, London, UK:Springer , ISBN-10: 3-540-60676-9 Google Scholar
  • 23. Nolfi, S. , Floreano, D. Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. 2000, 03, Cambridge, MA:The MIT Press , ISBN-10: 0-262-64056-2 Google Scholar
  • 24. Ortiz-Bayliss, J.C. , Terashima-Marin, H. , Ross, P. , Conant-Pablos, S.E. (2011). ‘Evolution of neural networks topologies and learning parameters to produce hyper-heuristics for constraint satisfaction problems’. 261-262, GECCO (Companion) Google Scholar
  • 25. Peng, L. , Woo, P-Y. Neural-Fuzzy Control System for Robotic Manipulators, IEEE Control Systems Magazine. 2002, 02, IEEE Press, ISSN: 0272-1708 Google Scholar
  • 26. Poland, M.P. , Nugent, C.D. , Wang, H. , Chen, L. (2012). ‘Genetic algorithm and pure random search for exosensor distribution optimization’. Int. J. of Bio-Inspired Computation. 4, 6, 359-372 AbstractGoogle Scholar
  • 27. Rojas, R. (1996). Neural Networks – A Systematic Introduction. Berlin:Springer Google Scholar
  • 28. Rosales-Peréz, A. , Reyes-Garcia, C.A. , Gomez-Gil, P. (2011). ‘Genetic fuzzy relational neural network for infant cry classification’. MCPR. 288-296 Google Scholar
  • 29. Sánchez, D. , Melin, P. , Castillo, O. (2011). ‘A new model of modular neural networks with fuzzy granularity for pattern recognition and its optimization with hierarchical genetic algorithms’. 7095, MICAI, 2, 331-342 Google Scholar
  • 30. Schmidt, M.D. , Lipson, H. (2007). ‘Coevolving fitness models for accelerating evolution and reducing evaluations’. Genetic Programming Theory and Practice. IV, Springer, 113-130, ISBN-10: 0-387-33375-4 Google Scholar
  • 31. Spolaor, N. , Lorena, A.C. , Lee, H.D. (2011). ‘Multi-objective genetic algorithm evaluation in feature selection, evolutionary multi-criterion optimization’. LNCS, Springer, 462-476, ISBN-13: 978-3-642-19892-2 Google Scholar
  • 32. Sumathi, S. , Hamsapriya, T. , Surekha, P. (2008). Evolutionary Intelligence: An Introduction to Theory and Applications with MATLAB. Heidelberg, Germany:Springer , ISBN-13: 978-3-540-75158-8 Google Scholar
  • 33. The Blue Brain Project EPFL [online] http://bluebrain.epfl.ch/ Google Scholar
  • 34. Trujillo, L. , Martinez, Y. , Melin, P. (2011). ‘How many neurons? A genetic programming answer’. 175-176, GECCO (Companion) Google Scholar
  • 35. Yang, X-S. (2011). ‘Bat algorithm for multi-objective optimization’. Int. J. of Bio-Inspired Computation. 3, 5, 267-274 AbstractGoogle Scholar