Bacterial Foraging Optimization Algorithm for neural network learning enhancement

Abstract

Backpropagation algorithm is widely used to solve many real-world problems, using the concept of Multilayer Perceptron. However, main disadvantages of Backpropagation are the convergence rate of it being relatively slow, and it is often trapped in the local minima. To solve this problem, it is found in the literatures, an evolutionary algorithm such as Particle Swarm Optimization algorithm is applied in feedforward neural network to optimize the learning process in terms of convergence rate and classification accuracy but this process needs longer training time. Hence to provide an alternative solution this study introduced, Bacterial Foraging Optimization Algorithm to be utilized in feedforward neural network to enhance the learning process and improve its convergence rate and classification accuracy. The developed Bacterial Foraging Optimization Algorithm Feedforward Neural Network (BFOANN) is compared against Particle Swarm Optimization Feedforward Neural Network (PSONN). The results show that BFOANN outperforms PSONN with better convergence rate and classification accuracy.