WCBP: a new water cycle based back propagation algorithm for data classification

Water Cycle algorithm is a modern nature inspired meta-heuristic algorithm to provide derivative-free solution to optimize complex problems. The back-propagation neural network (BPNN) algorithm performs well on many complex data types but it possess the problem of network stagnancy and local minima. Therefore, this paper proposed the use of WC algorithm in combination with Back-Propagation neural network (BPNN) algorithm to solve the local minima problem in gradient descent trajectory. The performance of the proposed Water Cycle based Back-Propagation (WCBP) algorithm is compared with the conventional BPNN, ABC-BP and ABC-LM algorithms on selected benchmark classification problems from UCI Machine Learning Repository. The simulation results show that the BPNN training process is highly enhanced when combined with WC algorithm.