Learning and Evolution in Artificial Neural Networks: A Comparison Study

Eva Volna

Abstract

This paper aims at learning and evolution in artificial neural networks. Here is presented a system evolving populations of neural nets that are fully connected multilayer feedforward networks with fixed architecture solving given tasks. The system is compared with gradient descent weight training (like backpropagation) and with hybrid neural network adaptation. All neural networks have the same architecture and solve the same problems to be able to be compared mutually. In order to test the efficiency of described algorithms, we applied them to the Fisher's Iris data set [1] that is the bench test database from the area of machine learning.

References

  1. http://en.wikipedia.org/wiki/Iris_flower_data_set (from 16/1/2008)
  2. Hertz, J., Krogh, A., and Palmer, R. Introduction to the Theory of Neural Computation. Reading, MA: Addison-Wesley, 1991.
  3. Lang, K. J. Waibel, A. H., and Hinton, G. E.“A time-delay neural network architecture for isolated word recognition,” Neural Networks, vol. 3, no. 1, pp. 33-43, 1990.
  4. Fels S. S. and Hinton, G. E. “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.
  5. Knerr, S., Personnaz, L., and G. Dreyfus, “Handwritten digit recognition by neural networks with single-layer training,” IEEE Trans, Neural Networks, vol. 3, pp. 962-968, Nov. 1992, neural networks that uses genetic-algorithm techniques.”
  6. Bäck, T., Hammel, U., and Schwefel, H.-P. “Evolutionary computation: Comments on the history and current state”. IEEE Trans, Evolutionary Computation, vol. 1, pp. 3-17, Apr. 1997.
  7. Yao, X. “Evolving artificial neural networks”, In Proceedings of the IEEE 89 (9) 1423-1447, 1999.
  8. Montana, D., and Davis, L. “Training feedforward neural networks using genetic algorithms.” In Proceedings 11th Int. Joint Conf. Artificial Intelligence, pp. 762-767San Mateo, CA: Morgan Kaufmann, 1989.
  9. Pujol, J. C. F. and Poli, R. Evolving the topology and the weights of neural networks using a dual representation, Applied Intelligence, 8(1):73-84, 1998.
  10. Angeline, P. J., Saunders, G, M., and Pollack, J. B. An evolutionary algorithm that constructs recurrent neural networks, IEEE Transactions on Neural Networks, pages 54-65, 1994.
  11. Janson D. J. and Frenzel, J. F. “Application of genetic algorithms to the training of higher order neural networks,” J, Syst, Eng., vol. 2, pp. 272-276, 1992.
  12. Lehotsky, M. Olej, V. and Chmurny, J. “Pattern recognition based on the fuzzy neural networks and their learning by modified genetic algorithms,” Neural Network World, vol. 5, no. 1, pp. 91-97, 1995.
  13. Lee, S.-W. “Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural network,” IEEE Trans. Pattern Anal. Machine Intell., vol. 18, pp. 648-652, June 1996.
  14. Merelo, J. J. Paton, M. Canas, A., Prieto, A. and Moran, F. “Optimization of a competitive learning neural network by genetic algorithms,” in Proc. Int. Workshop Artificial Neural Networks (IWANN'93), Lecture Notes in Computer Science, vol. 686, Berlin, Germany: Springer-Verlag, 1993, pp. 185-192.
  15. Wang, D. D. and Xu, J. “Fault detection based on evolving LVQ neural networks,” in Proc. 1996 IEEE Int. Conf. Systems, Man and Cybernetics, vol. 1, pp. 255-260.
Download


Paper Citation


in Harvard Style

Volna E. (2008). Learning and Evolution in Artificial Neural Networks: A Comparison Study . In Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008) ISBN 978-989-8111-33-3, pages 10-17. DOI: 10.5220/0001506900100017


in Bibtex Style

@conference{anniip08,
author={Eva Volna},
title={Learning and Evolution in Artificial Neural Networks: A Comparison Study},
booktitle={Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)},
year={2008},
pages={10-17},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001506900100017},
isbn={978-989-8111-33-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)
TI - Learning and Evolution in Artificial Neural Networks: A Comparison Study
SN - 978-989-8111-33-3
AU - Volna E.
PY - 2008
SP - 10
EP - 17
DO - 10.5220/0001506900100017