Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks


KARABOĞA D. , AKAY B. , ÖZTÜRK C.

4th International Conference on Modeling Decisions for Artificial Intelligence, Kitakyushu, Japonya, 16 Ağustos 2007 - 18 Ağustos 2008, cilt.4617, ss.318-321 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 4617
  • Basıldığı Şehir: Kitakyushu
  • Basıldığı Ülke: Japonya
  • Sayfa Sayıları: ss.318-321

Özet

T raining an artificial neural network is an optimization task since it is desired to find optimal weight set of a neural network in training process. Traditional training algorithms has some drawbacks such as getting stuck in local minima and computational complexity. Therefore, evolutionary algorithms are employed to train neural networks to overcome these issues. In this work, Artificial Bee Colony (ABC) Algorithm which has good exploration and exploitation capabilities in searching optimal weight set is used in training neural networks.