A dynamic metaheuristic optimization model inspired by biological nervous systems: Neural network algorithm

• Published in: Applied soft computing Vol. 71; pp. 747 - 782
• Main Authors: Sadollah, Ali, Sayyaadi, Hassan, Yadav, Anupam
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2018
• Subjects: Artificial neural networks; Global optimization; Iterative convergence; Metaheuristics; Neural network algorithm; Global optimization; Iterative convergence; Neural network algorithm; Metaheuristics; Artificial neural networks
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2018.07.039

[Display omitted] •A dynamic optimization model Neural Network Algorithm (NNA) is proposed.•NNA is inspired by the structure of ANNs and biological nervous systems.•NNA is a parallel associated memory-based sequential-batch learning optimizer.•Convergence proof has been carried out for a random initial population.•NNA outperformed reported metaheuristic methods obtaining better quality solutions. In this research, a new metaheuristic optimization algorithm, inspired by biological nervous systems and artificial neural networks (ANNs) is proposed for solving complex optimization problems. The proposed method, named as neural network algorithm (NNA), is developed based on the unique structure of ANNs. The NNA benefits from complicated structure of the ANNs and its operators in order to generate new candidate solutions. In terms of convergence proof, the relationship between improvised exploitation and each parameter under asymmetric interval is derived and an iterative convergence of NNA is proved theoretically. In this paper, the NNA with its interconnected computing unit is examined for 21 well-known unconstrained benchmarks with dimensions 50–200 for evaluating its performance compared with the state-of-the-art algorithms and recent optimization methods. Besides, several constrained engineering design problems have been investigated to validate the efficiency of NNA for searching in feasible region in constrained optimization problems. Being an algorithm without any effort for fine tuning initial parameters and statistically superior can distinguish the NNA over other reported optimizers. It can be concluded that, the ANNs and its particular structure can be successfully utilized and modeled as metaheuristic optimization method for handling optimization problems.