Research Article
BibTex RIS Cite

İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar

Year 2022, Volume: 15 Issue: 1, 38 - 43, 27.06.2022

Ebubekir Kaya

https://doi.org/10.54525/tbbmd.1071656

Abstract

Sistem kimliklendirme ve modelleme için en yaygın kullanılan yapay zekâ tekniklerinden biri yapay sinir ağlarıdır. Yapay sinir ağları ile etkili sonuçlar elde etmek için etkili bir eğitim sürecine ihtiyaç duyulmaktadır. Meta-sezgisel algoritmalar pek çok gerçek dünya probleminin çözümünde başarılı bir şekilde kullanılmaktadır. Özellikle yapay sinir ağı eğitiminde, ağa ait parametrelerin optimizasyonu gerekmektedir. Son zamanlarda, bu amaçla meta-sezgisel algoritmalar kullanılmakta ve başarılı sonuçlar elde edilmektedir. Literatürde pek çok meta-sezgisel algoritma bulunmaktadır. Meta-sezgisel algoritmaların performansları problem türüne göre farklılık göstermektedir. Bu çalışma kapsamında ileri beslemeli yapay sinir ağının eğitiminde, yapay arı koloni algoritması, parçacık sürü algoritması, armoni arama, arı algoritması, çiçek tozlaşma algoritması ve guguk kuşu arama gibi popüler meta-sezgisel algoritmaların performansları değerlendirilmiştir. Uygulamalar için XOR, 2-bit parity ve 3-bit parity problemleri kullanılmıştır. Tüm problemler için elde edilen sonuçlar çözüm kalitesi ve yakınsama hızı açısından değerlendirilmiştir. Genel olarak ilgili problemlerin çözümü için meta-sezgisel algoritma tabanlı ileri yapay sinir ağı eğitiminin başarılı olduğu gözlemlenmiştir. En iyi sonuçlar ise yapay arı koloni algoritması ve guguk kuşu arama ile bulunmuştur.

Keywords

İleri beslemeli yapay sinir ağı Meta-sezgisel algoritmalar Yapay sinir ağı eğitimi Modelleme Optimizasyon

References

  • Abiodun, O.I., Jantan, A., Omolara, A.E., Dada, K.V., Mohamed, N.A., Arshad, H. State-of-the-art in artificial neural network applications: A survey, Heliyon, 2018, 4(11), pp. e00938.
  • Ozturk, C., Karaboga, D. Hybrid artificial bee colony algorithm for neural network training, in Editor (Ed.)^(Eds.): Book Hybrid artificial bee colony algorithm for neural network training (IEEE, 2011, edn.), pp. 84-88.
  • Ozkan, C., Ozturk, C., Sunar, F., Karaboga, D. The artificial bee colony algorithm in training artificial neural network for oil spill detection, Neural Network World, 2011, 21(6), pp. 473.
  • Kaya, E., Kaya, C.B.A Novel Neural Network Training Algorithm for the Identification of Nonlinear Static Systems: Artificial Bee Colony Algorithm Based on Effective Scout Bee Stage, Symmetry, 2021, 13 (3), pp. 419.
  • Zhang, J.-R., Zhang, J., Lok, T.-M., Lyu, M.R. A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training, Applied mathematics and computation, 2007, 185(2), pp. 1026-1037.
  • Das, G., Pattnaik, P.K., Padhy, S.K. Artificial neural network trained by particle swarm optimization for non-linear channel equalization, Expert Systems with Applications, 2014, 41(7), pp. 3491-3496.
  • Xie, K., Yi, H., Hu, G., Li, L., Fan, Z. Short-term power load forecasting based on Elman neural network with particle swarm optimization, Neurocomputing, 2020, 416, pp. 136-142.
  • Tavakoli, S., Valian, E., ,Mohanna, S. Feedforward neural network training using intelligent global harmony search, Evolving Systems, 2012, 3 (2), pp. 125-131.
  • Elattar, E.E., Elsayed, S.K., Farrag, T.A. Hybrid Local General Regression Neural Network and Harmony Search Algorithm for Electricity Price Forecasting, IEEE Access, 2020, 9, pp. 2044-2054.
  • Kaya, C.B., Ebubekir, K. A Novel Approach Based to Neural Network and Flower Pollination Algorithm to Predict Number of COVID-19 Cases, Balkan Journal of Electrical and Computer Engineering, 2021, 9 (4), pp. 327-336.
  • Chiroma, H., Khan, A., Abubakar, A.I., Saadi, Y., Hamza, M.F., Shuib, L., Gital, A.Y., Herawan, T. A new approach for forecasting OPEC petroleum consumption based on neural network train by using flower pollination algorithm, Applied Soft Computing, 2016, 48, pp. 50-58.
  • Valian, E., Mohanna, S., Tavakoli, S. Improved cuckoo search algorithm for feedforward neural network training, International Journal of Artificial Intelligence & Applications, 2011, 2(3), pp. 36-43.
  • Nawi, N.M., Khan, A., Rehman, M. A New Levenberg Marquardt Based Back Propagation Algorithm Trained with Cuckoo Search, Procedia Technology, 2013, 11, pp. 18-23.
  • Najafi, F. The Role of Metaheuristic Algorithm in Weight Training and Architecture Evolving of Feedforward Neural Networks, 2020.
  • Irmak, B., Gülcü, Ş. Training of the Feed-Forward Artificial Neural Networks Using Butterfly Optimization Algorithm, MANAS Journal of Engineering, 2021, 9(2), pp160-168.
  • Gulcu, Ş. Training of The Artificial Neural Networks Using States of Matter Search Algorithm, International Journal of Intelligent Systems and Applications in Engineering, 2020, 8(3), pp.131-136.
  • Bousmaha, R., Hamou, R. M., Amine, A. Optimizing Connection Weights in Neural Networks Using Hybrid Metaheuristics Algorithms, International Journal of Information Retrieval Research (IJIRR), 2022, 12(1), pp.1-21.
  • Mousavirad, S. J., Jalali, S. M. J., Ahmadian, S., Khosravi, A., Schaefer, G., Nahavandi, S. Neural Network Training Using a Biogeography-Based Learning Strategy, In International Conference on Neural Information Processing, 2020 November, Springer, Cham, pp. 147-155.

The Meta-Heuristics Approaches in Training Feed-Forward Neural Networks

Year 2022, Volume: 15 Issue: 1, 38 - 43, 27.06.2022

Ebubekir Kaya

https://doi.org/10.54525/tbbmd.1071656

Abstract

Artificial neural network is one of the most widely used artificial intelligence techniques for system identification and modeling. An effective training process is needed to obtain effective results with artificial neural networks. Metaheuristic algorithms have been used successfully in solving many real-world problems. Especially, optimization of the parameters of the network is required in artificial neural network training. Recently, metaheuristic algorithms have been used for this purpose and successful results have been obtained. There are many metaheuristic algorithms in the literature. The performances of meta-heuristic algorithms can differ according to the problem type. In this study, the performances of popular metaheuristic algorithms such as artificial bee colony algorithm, particle swarm optimization, harmony search, bee algorithm, flower pollination algorithm and cuckoo search are evaluated in the training of feed forward neural network. XOR, 2-bit parity and 3-bit parity problems are utilized for applications. The results obtained for all problems are evaluated in terms of solution quality and convergence speed. In general, it has been observed that neural network training based on metaheuristic algorithm is successful for solving related problems. The best results are found by using artificial bee colony algorithm and cuckoo search.

Keywords

Feed forward neural network Metaheuristic algorithms Neural network training Modeling Optimization

References

  • Abiodun, O.I., Jantan, A., Omolara, A.E., Dada, K.V., Mohamed, N.A., Arshad, H. State-of-the-art in artificial neural network applications: A survey, Heliyon, 2018, 4(11), pp. e00938.
  • Ozturk, C., Karaboga, D. Hybrid artificial bee colony algorithm for neural network training, in Editor (Ed.)^(Eds.): Book Hybrid artificial bee colony algorithm for neural network training (IEEE, 2011, edn.), pp. 84-88.
  • Ozkan, C., Ozturk, C., Sunar, F., Karaboga, D. The artificial bee colony algorithm in training artificial neural network for oil spill detection, Neural Network World, 2011, 21(6), pp. 473.
  • Kaya, E., Kaya, C.B.A Novel Neural Network Training Algorithm for the Identification of Nonlinear Static Systems: Artificial Bee Colony Algorithm Based on Effective Scout Bee Stage, Symmetry, 2021, 13 (3), pp. 419.
  • Zhang, J.-R., Zhang, J., Lok, T.-M., Lyu, M.R. A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training, Applied mathematics and computation, 2007, 185(2), pp. 1026-1037.
  • Das, G., Pattnaik, P.K., Padhy, S.K. Artificial neural network trained by particle swarm optimization for non-linear channel equalization, Expert Systems with Applications, 2014, 41(7), pp. 3491-3496.
  • Xie, K., Yi, H., Hu, G., Li, L., Fan, Z. Short-term power load forecasting based on Elman neural network with particle swarm optimization, Neurocomputing, 2020, 416, pp. 136-142.
  • Tavakoli, S., Valian, E., ,Mohanna, S. Feedforward neural network training using intelligent global harmony search, Evolving Systems, 2012, 3 (2), pp. 125-131.
  • Elattar, E.E., Elsayed, S.K., Farrag, T.A. Hybrid Local General Regression Neural Network and Harmony Search Algorithm for Electricity Price Forecasting, IEEE Access, 2020, 9, pp. 2044-2054.
  • Kaya, C.B., Ebubekir, K. A Novel Approach Based to Neural Network and Flower Pollination Algorithm to Predict Number of COVID-19 Cases, Balkan Journal of Electrical and Computer Engineering, 2021, 9 (4), pp. 327-336.
  • Chiroma, H., Khan, A., Abubakar, A.I., Saadi, Y., Hamza, M.F., Shuib, L., Gital, A.Y., Herawan, T. A new approach for forecasting OPEC petroleum consumption based on neural network train by using flower pollination algorithm, Applied Soft Computing, 2016, 48, pp. 50-58.
  • Valian, E., Mohanna, S., Tavakoli, S. Improved cuckoo search algorithm for feedforward neural network training, International Journal of Artificial Intelligence & Applications, 2011, 2(3), pp. 36-43.
  • Nawi, N.M., Khan, A., Rehman, M. A New Levenberg Marquardt Based Back Propagation Algorithm Trained with Cuckoo Search, Procedia Technology, 2013, 11, pp. 18-23.
  • Najafi, F. The Role of Metaheuristic Algorithm in Weight Training and Architecture Evolving of Feedforward Neural Networks, 2020.
  • Irmak, B., Gülcü, Ş. Training of the Feed-Forward Artificial Neural Networks Using Butterfly Optimization Algorithm, MANAS Journal of Engineering, 2021, 9(2), pp160-168.
  • Gulcu, Ş. Training of The Artificial Neural Networks Using States of Matter Search Algorithm, International Journal of Intelligent Systems and Applications in Engineering, 2020, 8(3), pp.131-136.
  • Bousmaha, R., Hamou, R. M., Amine, A. Optimizing Connection Weights in Neural Networks Using Hybrid Metaheuristics Algorithms, International Journal of Information Retrieval Research (IJIRR), 2022, 12(1), pp.1-21.
  • Mousavirad, S. J., Jalali, S. M. J., Ahmadian, S., Khosravi, A., Schaefer, G., Nahavandi, S. Neural Network Training Using a Biogeography-Based Learning Strategy, In International Conference on Neural Information Processing, 2020 November, Springer, Cham, pp. 147-155.
There are 18 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Makaleler(Araştırma)
Authors

Ebubekir Kaya 0000-0001-8576-7750

Early Pub Date June 27, 2022
Publication Date June 27, 2022
Published in Issue Year 2022 Volume: 15 Issue: 1

Cite

APA Kaya, E. (2022). İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi, 15(1), 38-43. https://doi.org/10.54525/tbbmd.1071656
AMA Kaya E. İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar. TBV-BBMD. June 2022;15(1):38-43. doi:10.54525/tbbmd.1071656
Chicago Kaya, Ebubekir. “İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi 15, no. 1 (June 2022): 38-43. https://doi.org/10.54525/tbbmd.1071656.
EndNote Kaya E (June 1, 2022) İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi 15 1 38–43.
IEEE E. Kaya, “İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar”, TBV-BBMD, vol. 15, no. 1, pp. 38–43, 2022, doi: 10.54525/tbbmd.1071656.
ISNAD Kaya, Ebubekir. “İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi 15/1 (June 2022), 38-43. https://doi.org/10.54525/tbbmd.1071656.
JAMA Kaya E. İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar. TBV-BBMD. 2022;15:38–43.
MLA Kaya, Ebubekir. “İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi, vol. 15, no. 1, 2022, pp. 38-43, doi:10.54525/tbbmd.1071656.
Vancouver Kaya E. İleri Beslemeli Yapay Sinir Ağının Eğitiminde Meta-Sezgisel Yaklaşımlar. TBV-BBMD. 2022;15(1):38-43.
 Download Cover Image

Article Acceptance

Use user registration/login to upload articles online.

The acceptance process of the articles sent to the journal consists of the following stages:

1. Each submitted article is sent to at least two referees at the first stage.

2. Referee appointments are made by the journal editors. There are approximately 200 referees in the referee pool of the journal and these referees are classified according to their areas of interest. Each referee is sent an article on the subject he is interested in. The selection of the arbitrator is done in a way that does not cause any conflict of interest.

3. In the articles sent to the referees, the names of the authors are closed.

4. Referees are explained how to evaluate an article and are asked to fill in the evaluation form shown below.

5. The articles in which two referees give positive opinion are subjected to similarity review by the editors. The similarity in the articles is expected to be less than 25%.

6. A paper that has passed all stages is reviewed by the editor in terms of language and presentation, and necessary corrections and improvements are made. If necessary, the authors are notified of the situation.

0

.   This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.