Parametric Optimization of Artificial Neural Networks for Signal Approximation Applications

J. Lane Thames, Randal Abler, Dirk Schaefer

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)
124 Downloads (Pure)

Abstract

Artificial neural networks are used to solve diverse sets of problems. However, the accuracy of the network’s output for a given problem domain depends on appropriate selection of training data as well as various design parameters that define the structure of the network before it is trained. Genetic algorithms have been used successfully for many types of optimization problems. In this paper, we describe a methodology that uses genetic algorithms to find an optimal set of configuration parameters for artificial neural networks such that the network’s approximation error for signal approximation problems is minimized.
Original languageEnglish
DOIs
Publication statusPublished - 2011
Event48th Annual ACM Southeast Conference - Kennesaw, Georgia, USA United States
Duration: 24 Mar 201126 Mar 2011

Conference

Conference48th Annual ACM Southeast Conference
CountryUSA United States
CityKennesaw, Georgia
Period24/03/1126/03/11

Keywords

  • Genetic algorithms
  • Artificial neural networks
  • parameter optimization

Fingerprint Dive into the research topics of 'Parametric Optimization of Artificial Neural Networks for Signal Approximation Applications'. Together they form a unique fingerprint.

Cite this