Entrenamiento de una red neuronal artificial usando el algoritmo simulated annealing


Authors

  • German Alonso Gómez Rojas
  • Juan Carlos Henao López
  • Harold Salazar Isaza

Abstract

La modificación de los pesos y bias con un algoritmo de entrenamiento de un perceptrón multicapa es un problema clásico de programación no lineal irrestricto. El presente trabajo muestra el desempeño del “Simulated Annealing” como algoritmo de entrenamiento de esta red neuronal resolviendo dos problemas clásicos en redes neuronales, el problema de la “Codificación” y el problema de la “Doble Espiral”. Resultados de buena calidad son obtenidos cuando se compara esta propuesta frente a algoritmos clásicos de entrenamiento.

Downloads

Download data is not yet available.

Downloads

Published

2004-01-05

How to Cite

Gómez Rojas, G. A., Henao López, J. C., & Salazar Isaza, H. (2004). Entrenamiento de una red neuronal artificial usando el algoritmo simulated annealing. Scientia Et Technica, 1(24). Retrieved from https://revistas.utp.edu.co/index.php/revistaciencia/article/view/7307

Issue

Vol. 1 No. 24 (2004)

Section

Eléctrica

License

Copyright (c) 2017 Scientia et technica

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The undersigned authors declare that the article submitted to the journal Scientia et Technica is an original work and that all its content is free of third-party copyright restrictions or has the corresponding authorizations. Consequently, the authors assume responsibility for any litigation or claim related to intellectual property rights, releasing the Technological University of Pereira and the journal Scientia et Technica from any liability.

If the submitted work is accepted for publication, the authors retain copyright to the article and grant the journal Scientia et Technica the right of first publication, as well as a non-exclusive, perpetual license to reproduce, edit, distribute, display, and publicly communicate the article in any medium or format, including print, electronic, databases, repositories, the Internet, or other scientific dissemination systems. The authors agree that the article will be published in open access and distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0).

The journal Scientia will respect in all cases the moral rights of the authors, in accordance with the provisions of article 30 of Law 23 of 1982 of the Republic of Colombia, recognizing the authorship of the work, the right to integrity and the right of disclosure, which are inalienable and non-waivable.