An Improved BP Neural Network Algorithm and its Application

Ming Jun Chen

doi:10.4028/www.scientific.net/AMM.543-547.2120

Paper Titles

Research and DSP Realization on the Improved Algorithms for PUCCH Format 2a/2b in TD-LTE System
p.2103

Chaotic Time Series Prediction Algorithm for Lori Mapping Based on Optimized BP Neural Network
p.2108

Research on Line Fuzzy Neural Network Learning Algorithm and its Application
p.2112

Ant Colony Algorithm Based on Improved Neural Network Algorithm and its Application
p.2116

An Improved BP Neural Network Algorithm and its Application
p.2120

An Improved K-Means Algorithm and its Application in Customer Classification of Network Enterprises
p.2124

Research on the Prediction Method for Library Reader Flow Based on Evolutionary Neural Network
p.2128

Integration Particle Swarm Algorithm and its Application in Neural Network
p.2133

Study on Three-Dimensional Reconstruction of the Individualized Maxillofacial Soft and Hard Tissue
p.2137

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 543-547An Improved BP Neural Network Algorithm and its...

An Improved BP Neural Network Algorithm and its Application

Abstract:

Back-propagation (BP) neural network algorithm is currently used most widely and grows fastest for its powful nonlinear simulation capability. However BP neural network is so easy to fall into local minima that it cant find the global optimum which limits its application in many fields. The paper, taking tax innovation teaching evaluation for example, advances a new evaluation algorithm based on improved BP neural network algorithm. Firstly an evaluation indicator system of tax major innovation teaching is designed through analyzing the specific characteristics of innovation teaching requirements. Secondly, in order to overcome the shortages of low convergence speed of original BP neural network algorithm, the paper improves BP algorithm through integrating BP algorithm and ant colony algorithm, ant improving the overall search method of integrated algorithm. Thirdly data from three universities are taken for examples to verify the validity and feasibility of the model and the experimental results show that the model can evaluate university innovation teaching practically.