Skip to Main Content
Training fuzzy neural network (FNN) is an optimization task which is desired to find optimal centers of the membership function and weights. Traditional training algorithms have some drawbacks such as getting stuck in local minima and computational complexity. This work presents FNN trained by artificial bee colony (ABC) optimization algorithm which has good exploration and exploitation capabilities. FNN trained by this algorithm is applied to speech recognition system and compares its performance with particle swarm optimization (PSO) algorithm and back-propagation (BP) algorithm. The experimental results prove that ABC algorithm has better recognition results and convergence speed than FNN trained by BP algorithm and has similar recognition results and convergence speed than FNN trained by PSO.