Irmak Büşra, Karakoyun Murat, Gülcü Şaban
Department of Computer Engineering, Necmettin Erbakan University, Konya, Turkey.
Soft comput. 2023;27(7):3887-3905. doi: 10.1007/s00500-022-07592-w. Epub 2022 Oct 20.
Artificial neural network (ANN) which is an information processing technique developed by modeling the nervous system of the human brain is one of the most powerful learning methods today. One of the factors that make ANN successful is its training algorithm. In this paper, an improved butterfly optimization algorithm (IBOA) based on the butterfly optimization algorithm was proposed for training the feed-forward artificial neural networks. The IBOA algorithm has the chaotic property which helps optimization algorithms to explore the search space more dynamically and globally. In the experiments, ten chaotic maps were used. The success of the IBOA algorithm was tested on 13 benchmark functions which are well known to those working on global optimization and are frequently used for testing and analysis of optimization algorithms. The Tent-mapped IBOA algorithm outperformed the other algorithms in most of the benchmark functions. Moreover, the success of the IBOA-MLP algorithm also has been tested on five classification datasets (xor, balloon, iris, breast cancer, and heart) and the IBOA-MLP algorithm was compared with four algorithms in the literature. According to the statistical performance metrics (sensitivity, specificity, precision, 1-score, and Friedman test), the IBOA-MLP outperformed the other algorithms and proved to be successful in training the feed-forward artificial neural networks.
人工神经网络（ANN）是一种通过模拟人类大脑神经系统开发的信息处理技术，是当今最强大的学习方法之一。使ANN成功的因素之一是其训练算法。本文提出了一种基于蝴蝶优化算法的改进蝴蝶优化算法（IBOA），用于训练前馈人工神经网络。IBOA算法具有混沌特性，有助于优化算法更动态、更全局地探索搜索空间。在实验中，使用了十种混沌映射。IBOA算法的性能在13个基准函数上进行了测试，这些函数为从事全局优化的人员所熟知，并且经常用于优化算法的测试和分析。在大多数基准函数中，帐篷映射的IBOA算法优于其他算法。此外，IBOA-MLP算法的性能也在五个分类数据集（异或、气球、鸢尾花、乳腺癌和心脏）上进行了测试，并将IBOA-MLP算法与文献中的四种算法进行了比较。根据统计性能指标（灵敏度、特异性、精度、F1分数和弗里德曼检验），IBOA-MLP算法优于其他算法，并证明在训练前馈人工神经网络方面是成功的。
