English

Using CODEQ to Train Feed-forward Neural Networks

Neural and Evolutionary Computing 2010-02-04 v1 Artificial Intelligence

Abstract

CODEQ is a new, population-based meta-heuristic algorithm that is a hybrid of concepts from chaotic search, opposition-based learning, differential evolution and quantum mechanics. CODEQ has successfully been used to solve different types of problems (e.g. constrained, integer-programming, engineering) with excellent results. In this paper, CODEQ is used to train feed-forward neural networks. The proposed method is compared with particle swarm optimization and differential evolution algorithms on three data sets with encouraging results.

Keywords

Cite

@article{arxiv.1002.0745,
  title  = {Using CODEQ to Train Feed-forward Neural Networks},
  author = {Mahamed G. H. Omran and Faisal al-Adwani},
  journal= {arXiv preprint arXiv:1002.0745},
  year   = {2010}
}

Comments

8 pages

R2 v1 2026-06-21T14:42:56.314Z