Training recurrent neural networks for dynamic system identification using parallel tabu search algorithm

Karaboga D., KALINLI A.

1997 IEEE International Symposium on Intelligent Control, İstanbul, Türkiye, 16 - 18 Temmuz 1997, ss.113-118 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/isic.1997.626424
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.113-118
  • Orta Doğu Teknik Üniversitesi Adresli: Hayır

Özet

There are several modern heuristic optimisation techniques such as neural networks, genetic algorithms, simulated annealing and tabu search algorithms. Of these algorithms, tabu search is quite new promising search technique for numeric problems, especially for non-linear problems. However, the converging speed of the standard tabu search to the global optimum is initial solution dependent since it is a form of iterative search. In this paper, a new model of tabu search which has been proposed by the authors to overcome the drawback of a standard tabu search is tested for training a recurrent neural network to identify dynamic systems.