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.

Hybrid algorithms are widely used today to increase the performance of existing algorithms. In this paper, a new hybrid algorithm called IMVOSA that is based on multi-verse optimizer (MVO) and simulated annealing (SA) is used. In this model, a new method called the black hole selection (BHS) is proposed, in which exploration and exploitation can be increased. In the BHS method, the acceptance probability feature of the SA algorithm is used to increase exploitation by searching for the best regions found by the MVO algorithm. The proposed IMVOSA algorithm has been tested on 50 benchmark functions. The performance of IMVOSA has been compared with other latest and well-known metaheuristic algorithms. The consequences show that IMVOSA produces highly successful and competitive results.