Real-Coded Quantum-Inspired Genetic Algorithm-Based BP Neural Network Algorithm

• Published in: Mathematical problems in engineering Vol. 2015; no. 2015; pp. 1 - 10
• Main Authors: Fu, Chengqun, Sun, Yangyang, Wang, Huaixiao, Liu, Jianyong, Guo, Jie
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2015; John Wiley & Sons, Inc
• Subjects: Algorithms; Back propagation networks; Binary codes; Colleges & universities; Computer simulation; Decoding; Genetic algorithms; Genetics; Global optimization; Heuristic; Learning; Machine learning; Mathematical analysis; Mathematical problems; Neural networks; Optimization
• ISSN: 1024-123X; 1026-7077; 1563-5147; 1563-5147
• DOI: 10.1155/2015/571295

The method that the real-coded quantum-inspired genetic algorithm (RQGA) used to optimize the weights and threshold of BP neural network is proposed to overcome the defect that the gradient descent method makes the algorithm easily fall into local optimal value in the learning process. Quantum genetic algorithm (QGA) is with good directional global optimization ability, but the conventional QGA is based on binary coding; the speed of calculation is reduced by the coding and decoding processes. So, RQGA is introduced to explore the search space, and the improved varied learning rate is adopted to train the BP neural network. Simulation test shows that the proposed algorithm is effective to rapidly converge to the solution conformed to constraint conditions.