摘要
为提高BP神经网络识别模型的准确性,提出了一种对粒子群优化的BP神经网络(PSO-BP)进行改进的方法。按卡方分布选取初始点,以蒙特卡洛方法进行PSO-BP算法寻找全局最优解。利用改进后算法的随机性来提高BP神经网络的收敛速度和精度。将该识别方法应用到英文字符识别领域,仿真结果表明,该改进的PSO-BP算法提高了英文字符识别的准确性。
In order to improve the accuracy of BP neural network identification model,an improved method for particle swarm optimization is proposed.The initial points are selected according to the chi-square distribution,and the pso-bp algorithm is used to find the global optimal solution by monte carlo method.The randomness of the improved algorithm is used to improve the convergence speed and accuracy of BP neural network.The method is applied to the field of English character recognition,and the simulation results show that the improved pso-bp algorithm improves the accuracy of English character recognition.s.
作者
金姝含
张华钦
徐滨
吴宇航
JIN Shu-han;ZHANG Hua-qin;XU Bin;WU Yu-hang(College of Sciences,North China University of Science and Technology,Tangshan Hebei 063210,China;College of Mechanical Engineering,North China University of Science and Technology,Tangshan Hebei 063210,China;Mathematical Modeling Innovation Lab,North China University of Science and Technology,Tangshan Hebei 063210,China;Hebei Key Laboratory of Data Science and Applications,Tangshan Hebei 063210,China;Tangshan Key Laboratory of Data Science,Tangshan Hebei 063210,China)
出处
《新一代信息技术》
2018年第1期8-13,共6页
New Generation of Information Technology
基金
国家自然基金资助项目(No.11601151)。
关键词
BP神经网络
粒子群优化算法
蒙特卡洛法
卡方分布
字符识别
BP neural network
Particle swarm optimization
Monte carlo method
Chi-square distribution
Character recognition
