COOT optimization algorithm on training artificial neural networks

Ozden A., İşeri İ.

KNOWLEDGE AND INFORMATION SYSTEMS, cilt.65, sa.8, ss.3353-3383, 2023 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 65 Sayı: 8
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1007/s10115-023-01859-w
  • Dergi Adı: KNOWLEDGE AND INFORMATION SYSTEMS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, ABI/INFORM, Applied Science & Technology Source, Computer & Applied Sciences, INSPEC
  • Sayfa Sayıları: ss.3353-3383
  • Anahtar Kelimeler: Metaheuristic, Neural network, Coot optimization, Classification
  • Ondokuz Mayıs Üniversitesi Adresli: Evet

Özet

In recent years, significant advancements have been made in artificial neural network models and they have been applied to a variety of real-world problems. However, one of the limitations of artificial neural networks is that they can getting stuck in local minima during the training phase, which is a consequence of their use of gradient descent-based techniques. This negatively impacts the generalization performance of the network. In this study, it is proposed a new hybrid artificial neural network model called COOT-ANN, which uses the coot optimization algorithm firstly for optimizing artificial neural networks parameters, a metaheuristic-based approach. The COOT-ANN model does not get stuck in local minima during the training phase due to the use of metaheuristic-based optimization algorithm. The results of the study demonstrate that the proposed method is quite successful in terms of accuracy, cross-entropy, F1-score, and Cohen's Kappa metrics when compared to gradient descent, scaled conjugate gradient, and Levenberg-Marquardt optimization techniques.