DocumentCode
2084904
Title
A parameter adjustment algorithm of BP neural network
Author
Xiaozhong, Li ; Qiu, Li
Author_Institution
Coll. of Comput. Sci. & Inf. Eng., Tianjin Univ. of Sci.&Technol., Tianjin, China
Volume
1
fYear
2008
fDate
17-19 Nov. 2008
Firstpage
892
Lastpage
895
Abstract
BP neural network converges slowly and usually falls into partial minimum points. In this paper a new parameter adjustment algorithm is proposed, using anterior accumulated information to modify momentum. The algorithm has characteristics of enhancing the network convergence rate, preventing vibration and reducing network errors. The simulation result indicates that the algorithm is more effective.
Keywords
backpropagation; neural nets; BP neural network; network convergence rate; network errors; parameter adjustment algorithm; Artificial neural networks; Computer science; Convergence; Educational institutions; Intelligent networks; Intelligent systems; Knowledge engineering; Neural networks; Pattern recognition; Signal processing algorithms;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
Conference_Location
Xiamen
Print_ISBN
978-1-4244-2196-1
Electronic_ISBN
978-1-4244-2197-8
Type
conf
DOI
10.1109/ISKE.2008.4731055
Filename
4731055
Link To Document