Encoding subcomponents in cooperative co-evolutionary recurrent neural networks

Chandra R., Frean M., Zhang M., Omlin C. W.

NEUROCOMPUTING, cilt.74, sa.17, ss.3223-3234, 2011 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 74 Sayı: 17
  • Basım Tarihi: 2011
  • Doi Numarası: 10.1016/j.neucom.2011.05.003
  • Dergi Adı: NEUROCOMPUTING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.3223-3234
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Cooperative coevolution employs evolutionary algorithms to solve a high-dimensional search problem by decomposing it into low-dimensional subcomponents. Efficient problem decomposition methods or encoding schemes group interacting variables into separate subcomponents in order to solve them separately where possible. It is important to find out which encoding schemes efficiently group subcomponents and the nature of the neural network training problem in terms of the degree of non-separability. This paper introduces a novel encoding scheme in cooperative coevolution for training recurrent neural networks. The method is tested on grammatical inference problems. The results show that the proposed encoding scheme achieves better performance when compared to a previous encoding scheme. (C) 2011 Elsevier B.V. All rights reserved.