Title :
Study on the Improved BP Algorithm and Application
Author :
Xu, Yuemei ; Zhang, Hong
Author_Institution :
Sch. of Comput. Sci. & Technol., China Univ. of Min. & Technol., Xuzhou, China
Abstract :
First, the paper analyzes the standard BP Algorithm. Toward the limitation of the standard BP algorithm, an improved BP algorithm is obtained by modifying the action function, regulating the learning rate and choosing the initial weights. And then a recognition example about license plate recognition technology is given to prove the improved BP algorithm. From the exam results, the improved BP algorithm has some advantages in fast convergence speed, short recognition time and high recognition rate.
Keywords :
backpropagation; action function; improved BP algorithm; learning rate regulation; license plate recognition; standard BP Algorithm; Biomembranes; Convergence; Information processing; Licenses; Neural networks; Neurofeedback; Neurons; Paper technology; Pattern recognition; Vehicles; BP Algorithm; neural network; pattern recognition; vehicle license plate recognition;
Conference_Titel :
Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-0-7695-3699-6
DOI :
10.1109/APCIP.2009.9