Home > CSC-OpenAccess Library > Manuscript Information

This is an Open Access publication published under CSC-OpenAccess Policy.

Evolutionary Algorithm for Optimal Connection Weights
in Artificial Neural Networks

G.V.R. Sagar, S. Venkata Chalam, Manoj Kumar Singh

Pages - 333 - 340 | Revised - 01-11-2011 | Published - 15-12-2011

Published in International Journal of Engineering (IJE)

MORE INFORMATION

KEYWORDS

Evolutionary algorithm,, Mean square error., Back-Propagation,

ABSTRACT

A neural network may be considered as an adaptive system that progressively self-organizes in order to approximate the solution, making the problem solver free from the need to accurately and unambiguously specify the steps towards the solution. Moreover, Evolutionary Artificial Neural Networks (EANNs) have the ability to progressively improve their performance on a given task by executing learning. An evolutionary computation gives adaptability for connection weights using feed forward architecture. In this paper, the use of evolutionary computation for feed-forward neural network learning is discussed. To check the validation of proposed method, XOR benchmark problem has been used. The accuracy of the proposed model is more satisfactory as compared to gradient method.

1 | Abdullah, L., & Pauzi, H. M. (2014).An effective model for carbon dioxide emissions prediction: comparison of artificial neural networks learning algorithms. international journal of computational intelligence and applications, 13(03), 1450014. |

2 | Rotich, N. (2014). Forecasting of wind speeds and directions with artificial neural networks. |

3 | Movement, F. S. M., & network, A. N. (2013).International journal of electronics and communication engineering & technology (IJECET). Journal Impact Factor, 4(5), 117-125. |

4 | Anifowose, F., Labadin, J., & Abdulraheem, A. (2013, December). Predicting Petroleum Reservoir Properties from Downhole Sensor Data using an Ensemble Model of Neural Networks. In Proceedings of Workshop on Machine Learning for Sensory Data Analysis (p. 27). ACM. |

5 | Sagar, G. V. R., & Chalam, S. V. (2012). Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network. International Journal of Computer Applications, 53(4), 23-28. |

1 | Google Scholar |

2 | CiteSeerX |

3 | refSeek |

4 | Scribd |

5 | SlideShare |

6 | PdfSR |

1 | X. Yao, “Evolution of connectionist networks,” in Preprints Int. Symp. AI, Reasoning & Creativity, Queensland, Australia, Griffith Univ., pp. 49–52. 1991. |

2 | “A review of evolutionary artificial neural networks,” Int. J. Intell. Syst., vol. 8, no. 4, pp. 539–567, 1993. |

3 | “Evolutionary artificial neural networks,” Int. J. Neural Syst., vol. 4, no. 3, pp. 203–222,1993. |

4 | T. Dartnall, Ed. Dordrecht, “The evolution of connectionist networks,” in Artificial Intelligence and Creativity, The Netherlands: Kluwer, pp. 233–243, 1994. |

5 | A. Kent and J. G. Williams, “Evolutionary artificial neural networks,” in Encyclopedia of Computer Science and Technology, vol. 33, , Eds. New York: Marcel Dekker, pp. 137–170,1995. |

6 | G. E. Hinton, “Connectionist learning procedures,” Artificial Intell., vol. 40, no. 1–3, pp. 185–234, Sept. 1989 |

7 | Rumelhart D. E., Hinton G. E., Williams R. J. “Learning representations by back propagating errors”, .Nature, 323, 533-536, 1986. |

8 | Rumclhart D. E., Hinton G. E., Williams R. J.: “ Learning errors” , Nature, Vol. 323, pp. 533-536, 1986. |

9 | Wcrobs P. J,: ” Back-propagation: Past and Future”, Proc. Neural Networks, San Diego, CA,1, 343-354, 1988. |

10 | Wilamowski B. M,: “ Neural Network Architectures and Learning Algorithms: How not to be Frustrated with Neural Networks, IEEE Industrial Electronics Magazine “, Vol. 3 No. 4, pp.56-63, Dec. 2009. |

11 | R. S. Sutton, “Two problems with back-propagation and other steepest-descent learning procedures for networks,” in Proc. 8th Annual Conf. Cognitive Science Society. Hillsdale,NJ: Erlbaum, pp. 823–831, 1986. |

12 | D. Whitley, T. Starkweather, and C. Bogart, “Genetic algorithms and neural networks:Optimizing connections and connectivity,” Parallel Comput., vol. 14, no. 3, pp. 347–361,1990 |

13 | J. Hertz, A. Krogh, and R. Palmer, Introduction to the Theory of Neural Computation.Reading, MA: Addison-Wesley, 1991. |

14 | D. R. Hush and B. G. Horne, “Progress in supervised neural networks,” IEEE Signal Processing Mag., vol. 10, pp. 8–39, Jan. 1993. |

15 | Y. Chauvin and D. E. Rumelhart, Eds., Back-propagation: Theory, Architectures, and Applications. Hillsdale, NJ: Erlbaum, 1995. |

16 | J. Hertz, A. Krogh, and R. Palmer, Introduction to the Theory of Neural Computation.Reading, MA: Addison-Wesley, 1991. |

17 | D. R. Hush and B. G. Horne, “Progress in supervised neural networks,” IEEE Signal Processing Mag., vol. 10, pp. 8–39, Jan. 1993. |

18 | Y. Chauvin and D. E. Rumelhart, Eds., Backpropagation: Theory, Architectures, and Applications. Hillsdale, NJ: Erlbaum, 1995. |

19 | M. F. Mřller, “A scaled conjugate gradient algorithm for fast supervised learning,” Neural Networks, vol. 6, no. 4, pp. 525–533, 1993. |

20 | K. J. Lang, A. H. Waibel, and G. E. Hinton, “A time-delay neural network architecture for isolated word recognition,” Neural Networks, vol. 3, no. 1, pp. 33–43, 1990. |

21 | S. Knerr, L. Personnaz, and G. Dreyfus, “Handwritten digit recognition by neural networks with single-layer training,” IEEE Trans. Neural Networks, vol. 3, pp. 962–968, Nov. 1992. |

22 | S. S. Fels and G. E. Hinton, “Glove-talk: A neural network interface between a data-glove and a speech synthesizer,” IEEE Trans. Neural Networks, vol. 4, pp. 2–8, Jan. 1993. |

23 | D. Whitley, T. Starkweather, and C. Bogart, “Genetic algorithms and neural networks:Optimizing connections and connectivity,” Parallel Comput., vol. 14, no. 3, pp. 347–361,1990. |

24 | D. Whitley, “The GENITOR algorithm and selective pressure: Why rank-based allocation of reproductive trials is best,” in Proc. 3rd Int. Conf. Genetic Algorithms and Their Applications, J. D. Schaffer, Ed. San Mateo, CA: Morgan Kaufmann, pp. 116–121, 1989. |

25 | P. Zhang, Y. Sankai, and M. Ohta, “Hybrid adaptive learning control of nonlinear system,” in Proc. 1995 American Control Conf. Part 4 (of 6), pp. 2744–2748, 1995. |

Mr. G.V.R. Sagar

GPREC - India

nusagar@gmail.com

Dr. S. Venkata Chalam

- Nigeria

Dr. Manoj Kumar Singh

- India