BG: a hybrid algorithm for MLP
Chun Lu, Bingxue Shi, Lu Chen · 2002
The proposed hybrid BG learning method for a Multilayer Feedforward Perceptron (MLP) blends the merits of both the Back-Propagation algorithm (BP) and the Genetic Algorithm (GA). BG has superior performance over both BP and GA because it learns from their strong points to offset their weakness. Results of the experiments including the XOR problem and the sin(x) function approximation have proved the good performance of the BG algorithm.