Polynomial approximation using particle swarm optimization of lineal enhanced neural networks with no hidden layers.

Mingo López, Fernando de and Muriel Fernández, Miguel Ángel and Gómez Blas, Nuria and Triviño G., Daniel (2012). Polynomial approximation using particle swarm optimization of lineal enhanced neural networks with no hidden layers.. "International Journal "Information Models and Analyses"", v. 1 (n. 3); pp. 203-219. ISSN 1314-6416.

Description

Title: Polynomial approximation using particle swarm optimization of lineal enhanced neural networks with no hidden layers.
Author/s:
  • Mingo López, Fernando de
  • Muriel Fernández, Miguel Ángel
  • Gómez Blas, Nuria
  • Triviño G., Daniel
Item Type: Article
Título de Revista/Publicación: International Journal "Information Models and Analyses"
Date: 2012
ISSN: 1314-6416
Volume: 1
Subjects:
Freetext Keywords: Neural Networks, Swarm Computing, Particle Swarm Optimization.
Faculty: E.U. de Informática (UPM)
Department: Organización y Estructura de la Información [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (3MB) | Preview

Abstract

This paper presents some ideas about a new neural network architecture that can be compared to a Taylor analysis when dealing with patterns. Such architecture is based on lineal activation functions with an axo-axonic architecture. A biological axo-axonic connection between two neurons is defined as the weight in a connection in given by the output of another third neuron. This idea can be implemented in the so called Enhanced Neural Networks in which two Multilayer Perceptrons are used; the first one will output the weights that the second MLP uses to computed the desired output. This kind of neural network has universal approximation properties even with lineal activation functions. 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 swarm-based model is applied to obtain the Neural Network, training the net with a Particle Swarm algorithm.

More information

Item ID: 15817
DC Identifier: http://oa.upm.es/15817/
OAI Identifier: oai:oa.upm.es:15817
Official URL: http://www.foibg.com/ijima/vol01/ijima-cv01.htm
Deposited by: Memoria Investigacion
Deposited on: 07 Nov 2013 17:33
Last Modified: 21 Apr 2016 16:07
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM