Research and Application of Improved BP Neural Network Algorithm
FU Yu
LI Qian
LIU Peng
Abstract：In order to solve the problem that the convergence speed of BP algorithm is slow and the local minimum value is easy to fall into the local minimum value,in improving the fast problem and stability of the neural network algorithm,the existing improved BP algorithm still has some imperfections. In this paper,the BP algorithm integrates the advantages of the genetic algo?rithm and changes into the compressed mapping genetic and the BP neural network. An algorithm for combining advantages. As the improved BP algorithm integrates the principle of compression mapping,it can help solve the slow convergence rate in the process of using the algorithm,and the algorithm can easily fall into the local minimum in the use of the algorithm. The improved BP algorithm will enhance the convergence speed of BP network structure,and will make up for the traditional defects of BP neural network. Com?pared with the traditional BP algorithm,the improved BP algorithm reduces the number of training steps and saves the training time. And through data experiment,it is feasible to apply the improved algorithm to practice.
Keywords：neural networkcompression mappingoptimizationweight
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1037-1041 )