Abstract
This article deals with the use of genetic algorithms to optimize the architecture of a neural network. After a brief recall of our original neural network (named Yprel network), we show that a simulated-annealing-like technique has been advantageously replaced by genetic operators. Indeed, tests on character recognition (NIST handwritten database) have shown that the generalization rate has been improved, the mean network size has been reduced by a factor 3 and the learning speed has been significantly increased. Moreover, a portable adaptive mutation probability has been introduced which enables a parameter-free learning.
Preview
Unable to display preview. Download preview PDF.
Bibliography
Belew R.K., Mc Inerney J., Schraudolph N.N. (1991). Evolving network: using the genetic algorithm with connectionnist learning. In Langton C.G., Taylor C., Farmer J.D., Rasmussen (Eds.), Artificial life II, SFI studies in the sciences of complexity, Vol X (pp.511–547). Reading, Massachusetts: Addison-Wesley.
Dobnikar A. (1995) Genetic synthesis of task oriented neural networks. In D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Artificial neural nets and genetic algorithms (pp.329–332). New-York:Springer-Verlag.
Gruau F. (1993). Genetic synthesis of modular neural networks. In S.Forrest (Eds.), Proceedings of the fifth International Conference on Genetic Algorithms (pp. 318–325). San Mateo, CA: M.Kaufmann.
Gruau F. (1994). Synthèse de réseaux de neurones par codage cellulaire et algorithmes génétiques, Ph. D. Thesis, France.
Harp S.A., Samad T., Guha A. (1989). Towards the genetic synthesis of neural networks. In D.J. Schaffer (Eds.), 3rd International Conference on Genetic Algorithms (pp.360–369). San Mateo, CA: M.Kaufmann.
Kitano H. (1990). Designing neural networks using genetic algorithms with graph generation system, In Complex Systems, 4, 461–476.
Kussul E.M., Baidyk T.N. (1995). Genetic algorithm for neurocomputer image recognition. In D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Artificial Neural Nets and Genetic Algorithms (pp. 120–123). New-York: Springer-Verlag.
Lecourtier Y., Ennaji A., Gilles F., Chavy P. (1993). Yprel networks and classification. In Proceedings of the 1993 IEEE International Conference on Systems, Man and Cybernetics Vol 3 (pp.463–468). New-York: IEEE.
Lecourtier Y., Ennaji A., Stocker E., Gilles F. (1995). Yprel networks, classification and incremental learning, Traitement du signal, Vol. 12, 6, 597–607.
Lis J. (1995). The synthesis of the ranked neural networks applying genetic algorithm with the dynamic probability of mutation. In J. Mira, F. Sandoval (Eds.), Proceedings of the 1995 International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation (pp. 498–504). New-York: Springer-Verlag.
Merrill J.W.L., Port R.F. (1991). Fractally configured neural networks, Neural Networks, 4, 53–60.
Michel O., Biondi J. (1995). From the chromosome to the neural network. In D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Artificial Neural Nets and Genetic Algorithms (pp.80–83). New-York: Springer-Verlag.
Miller G.F., Todd P.M., Hedge S.U. (1989). Designing neural networks using genetic algorithms. In J.D. Schaffer (Eds.), Proceedings of the Third International Conference on Genetic Algorithms (pp. 379–384). San Mateo: M.Kaufmann
Roberts S.G., Turega M. (1995). Evolving neural network structures: an evaluation of encoding techniques. In D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Artificial Neural Nets and Genetic Algorithms (pp.96–99). New-York: Springer-Verlag.
Schaffer J., Braun H. (1995). Optimizing classifiers for handwritten digits by genetic algorithms. In D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Artificial Neural Nets and Genetic Algorithms (pp.10–13). New-York: Springer-Verlag.
Stocker E., Ribert A., Lecourtier Y., Ennaji A., (1996). An incremental distributed classifier building. In 13th International Conference on Pattern Recognition (ICPR'96) Vol IV, (pp. 128–132). Washington: IEEE Computer Society Press.
Whitley D., Starkweaker T., Bogart C. (1990). Genetic algorithms and neural networks: optimizing connections and connectivity, Parallel Computing, 14, 347–361.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ribert, A., Stocker, E., Lecourtier, Y., Ennaji, A. (1997). Optimizing a neural network architecture with an adaptive parameter genetic algorithm. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032512
Download citation
DOI: https://doi.org/10.1007/BFb0032512
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive