Scopus
🔓 Açık Erişim YÖKSİS Eşleşti
Optimizing the learning process of multi-layer perceptrons using a hybrid algorithm based on MVO and SA
International Journal of Industrial Engineering Computations · Eylül 2022
YÖKSİS Kayıtları
Optimizing the Learning Process of Multi-layer Perceptrons Using a Hybrid Algorithm Based on MVO and SA
International Journal of Industrial Engineering Computations · 2022 SCI-Expanded
DOÇENT MURAT KÖKLÜ →
Optimizing the learning process of multi-layer perceptrons using a hybrid algorithm based on MVO and SA
INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING COMPUTATIONS · 2022 SCI-Expanded
PROFESÖR ADEM ALPASLAN ALTUN →
Makale Bilgileri
DergiInternational Journal of Industrial Engineering Computations
Yayın TarihiEylül 2022
Cilt / Sayfa13 · 617-640
Scopus ID2-s2.0-85136282229
Erişim🔓 Açık Erişim
Özet
Artificial neural networks (ANNs) are one of the artificial intelligence techniques used in real-world problems and applications encountered in almost all industries such as education, health, chemistry, food, informatics, logistics, transportation. ANN is widely used in many techniques such as optimization, modelling, classification and forecasting, and many empirical studies have been carried out in areas such as planning, inventory management, maintenance, quality control, econometrics, supply chain management and logistics related to ANN. The most important and just as hard stage of ANNs is the learning process. This process is about finding optimal values in the search space for different datasets. In this process, the values generated by training algorithms are used as network parameters and are directly effective in the success of the neural network (NN). In classical training techniques, problems such as local optimum and slow convergence are encountered. Meta-heuristic algorithms for the training of ANNs in the face of this negative situation have been used in many studies as an alternative. In this study, a new hybrid algorithm namely MVOSANN is suggested for the training of ANNs, using Simulated annealing (SA) and Multi-verse optimizer (MVO) algorithms. The suggested MVOSANN algorithm has been experimented on 12 prevalently classification datasets. The productivity of MVOSANN has been compared with 12 well-recognized and current meta-heuristic algorithms. Experimental results show that MVOSANN produces very successful and competitive results.
Yazarlar (3)
1
Ömer Yılmaz
2
A. A. Altun
3
Murat Koklu
ORCID: 0000-0002-2737-2360
Anahtar Kelimeler
Hybrid optimization algorithm
Meta-heuristic algorithms
Multi-layer perceptron
Multi-verse optimizer
Optimization
Simulated annealing
Training neural network
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Metrikler
6
Atıf
3
Yazar
7
Anahtar Kelime