A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems

Ching Long Su, S. M. Yang, W. L. Huang

Research output: Contribution to journalArticlepeer-review

18 Citations (Scopus)

Abstract

A two-stage algorithm combining the advantages of adaptive genetic algorithm and modified Newton method is developed for effective training in feedforward neural networks. The genetic algorithm with adaptive reproduction, crossover, and mutation operators is to search for initial weight and bias of the neural network, while the modified Newton method, similar to BFGS algorithm, is to increase network training performance. The benchmark tests show that the two-stage algorithm is superior to many conventional ones: steepest descent, steepest descent with adaptive learning rate, conjugate gradient, and Newton-based methods and is suitable to small network in engineering applications. In addition to numerical simulation, the effectiveness of the two-stage algorithm is validated by experiments of system identification and vibration suppression.

Original languageEnglish
Pages (from-to)12189-12194
Number of pages6
JournalExpert Systems With Applications
Volume38
Issue number10
DOIs
Publication statusPublished - 2011 Sep 15

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems'. Together they form a unique fingerprint.

Cite this