An optimization methodology for neural network weights and architectures

  • Ludermir T
  • Yamazaki A
  • Zanchettin C
  • 53

    Readers

    Mendeley users who have this article in their library.
  • 83

    Citations

    Citations of this article.

Abstract

This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques.

Author-supplied keywords

  • Multilayer perceptron (MLP)
  • Optimization of weights and architectures
  • Simulating annealing
  • Tabu search

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Teresa B. Ludermir

  • Akio Yamazaki

  • Cleber Zanchettin

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free