A New Multi-layer Perceptron Trainer based on Dragonfly Optimization Algorithm. (Dept. E )

Abstract

In this paper, Dragonfly Optimizer (DO) was used to train Multi-Layer Perceptron (MLP). DO was used to find the weights and biases of the MLP to achieve a minimum error and a high classification accuracy. Four standard classification datasets were used to benchmark the performance of the proposed method. In addition, the performance of the proposed method were compared with three well-known optimization algorithms, namely, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Grey Wolf Optimizer (GWO) which were used to train MLP also. The experimental results showed that the DO algorithm with the MLP was very competitive as it solved the local optima problem and achieved high accuracy