Training of the feed-forward artificial neural networks using butterfly optimization algorithm

Artificial Neural Network (ANN) learns from inputs and outputs. The values of the weights biases in ANN are updated according to Researchers have proposed algorithms train Multi-Layer Perceptron (MLP). However, classical techniques often face problems solving this optimization problem. They tend need large amounts computing time, memory. More importantly, they get stuck within local optimum produce poor-quality solutions. To overcome these difficulties, meta-heuristic been used MLP. In article, Butterfly Optimization Algorithm (BOA) which was designed by modeling behaviors butterflies for first time multi-layer perceptron. developed algorithm named BOA-MLP where BOA optimized success tested on five data sets (iris, breast cancer, heart, balloon xor) frequently literature. experiments, compared with BAT-MLP, SMS-MLP BP algorithms. average standard deviation mean squared error, classification accuracy, sensitivity, specificity, precision F1-score were as performance metrics. According experimental results, it is seen that surpasses all shows superior success.