An optimizing BP neural network algorithm based on genetic algorithm

• Published in: The Artificial intelligence review Vol. 36; no. 2; pp. 153 - 162
• Main Authors: Ding, Shifei, Su, Chunyang, Yu, Junzhao
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.08.2011; Springer Nature B.V
• Subjects: Artificial Intelligence; Back propagation; Back propagation networks; Computer Science; Genetic algorithms; Hierarchies; Mutation; Neural networks; Optimization; Optimization algorithms; Population; Weightlifting; Genetic algorithm (GA); Connection weight; BP neural network; UCI data
• ISSN: 0269-2821; 1573-7462
• DOI: 10.1007/s10462-011-9208-z

A back-propagation (BP) neural network has good self-learning, self-adapting and generalization ability, but it may easily get stuck in a local minimum, and has a poor rate of convergence. Therefore, a method to optimize a BP algorithm based on a genetic algorithm (GA) is proposed to speed the training of BP, and to overcome BP’s disadvantage of being easily stuck in a local minimum. The UCI data set is used here for experimental analysis and the experimental result shows that, compared with the BP algorithm and a method that only uses GA to learn the connection weights, our method that combines GA and BP to train the neural network works better; is less easily stuck in a local minimum; the trained network has a better generalization ability; and it has a good stabilization performance.