medigraphic.com

2001, Number 1

<< Back Next >>

Rev Mex Ing Biomed 2001; 22 (1)

Definition of neuronal net for classification away from evolutive program

Martínez LAE, Goddard CJ

Language: Spanish
References: 11
Page: 4-11
PDF size: 135.79 Kb.


ABSTRACT

Artificial neural nets called Multi-layer Perceptrons (MP) are an extremely useful tool for solving classification problems. It has been shown that MPs with a single hidden layer can satisfactorily separate the classes involved in a given problem: however the number of hidden units required is unknown as there is no exact method for calculating them. The present work describes a way, using an evolutionary program (EP) with variable length chromosomes, of finding a suitable number of hidden units, as well as the weights on all the connections, thereby defining the architecture of a MP for a given classification problem. Only the number of input and output units are considered given. The operators used by the EP are selection and two forms of mutation, and these are specified in the paper.


REFERENCES

  1. Arturo Hernández Aguirre, «Introducción a las Redes Neuronales Artificiales», Soluciones Avanzadas, Año 7, No. 63, pp. 25-34, nov. De 1998.

  2. José R. Hilera, Víctor J. Martínez. “Redes Neuronales Artificiales.

  3. Fundamentos, modelos y aplicaciones”, Addison-Wesley Iberoamerica, 1987.

  4. Mohamad H. Hassoun, “Fundamentals of Artificial Neural Networks”, The MIT Press, 1995.

  5. David J. Montana, “Neural Network Weight Selection Using Genetic Algorithms”, capitulo 5 de Intelligent Hybrid Systems, Goonatilake and Khebbal (Eds.), John Wiley & Sons, 1995.

  6. Frédéric Gruau, “Genetic Programming of Neural Networks: Theory and Practice” capitulo 13 de Intelligent Hybrid Systems, Goonatilake and Khebbal (Eds.), John Wiley & Sons, 1995.

  7. Peter J. Angeline, Gregory M. Saunders y Jordan B. Pollack, “An Evolutionary Algorithm that Constructs Recurrent Neural Networks”, IEEE Transactions on Neural Networks, 5 (1), pp. 54-65, 1994.

  8. Xin Yao, “Evolving Artificial Neural Networks”, Proc. of the IEEE, 87(9):1423-1447, September 1999.

  9. David B. Fogel, “Evolutionary Computation. Toward a New Philosophy of Machine Intelligence”, The Institute of Electrical and Electronic Engineers, New York, 1995.

  10. R.A. Fisher,”The use of multiple measurements in taxonomic problems,” Annual Eugenics, 7, Part II, pp. 179-188, 1936.

  11. [Apoyo de Conacyt No. 400200-5-31929A]




2020     |     www.medigraphic.com