Grammatical swarm and particle swarm optimization models applied to neural network learning and topology definition

  • Authors:

  • Nuria Gómez;Luis F. Mingo;Juan Garitagoitia;Victor Martinez;Jose A. Calvo Manzano

  • Affiliations:

  • Universidad Politécnica de Madrid, Escuela Universitaria de Informática, Madrid, Spain;Universidad Politécnica de Madrid, Escuela Universitaria de Informática, Madrid, Spain;Universidad Politécnica de Madrid, Escuela Universitaria de Informática, Madrid, Spain;Universidad Politécnica de Madrid, Escuela Universitaria de Informática, Madrid, Spain;Universidad Politécnica de Madrid, Facultad de Informática, Madrid, Spain

  • Venue:
  • CIMMACS'09 Proceedings of the 8th WSEAS International Conference on Computational intelligence, man-machine systems and cybernetics
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

There exists a clear difference between cooperative and competitive strategies. The former ones are based on the swarm colonies, in which all individuals share its knowledge about the goal in order to pass such information to other individuals to get optimum solution. The latter ones are based on genetic models, that is, individuals can die and new individuals are created combining information of alive one; or are based on molecular/celular behaviour passing information from one structure to another. A Grammatical Swarm model is applied to obtain the Neural Network topology of a given problem, training the net with a Particle Swarm algorithm. This paper just shows some ideas in order to obtain an automatic way to define the most suitable neural network topology for a given patter set.