Global Optimisation in Neural Network Training

Lucas Chi Kwong Hui, Kwok-Yan Lam, Chee Weng CheaNeural Computing and Applications 1997 · OpenReview

Abstract

This paper presents a new neural network training scheme for pattern recognition applications. Our training technique is a hybrid scheme which involves, firstly, the use of the efficient BFGS optimisation method for locating minima of the total error function and, secondly, the use of genetic algorithms for finding a global minimum. This paper also describes experiments that compare the performance of our scheme with three other hybrid schemes of this kind when applied to challenging pattern recognition problems. Experiments have shown that our scheme gives better results than others.
BibTeX
@article{hui1997global,
  author = {Lucas Chi Kwong Hui and Kwok-Yan Lam and Chee Weng Chea},
  title = {{Global Optimisation in Neural Network Training}},
  journal = {Neural Computing and Applications},
  year = {1997},
  url = {https://openreview.net/forum?id=LzxRnxkRik},
}

Loading related content...

Figure