Conference Proceeding

The analysis of convergence of hybrid algorithm based on Neural Network and Genetic Algorithm

College of Info. Science and Engi, Shan Dong University of Scienceand Technology, QingDao, 266510. E-mail: ;
11/2005; DOI:10.1109/ICNNB.2005.1614604 ISBN: 0-7803-9422-4 pp.232- 235 In proceeding of: Neural Networks and Brain, 2005. ICNN&B '05. International Conference on, Volume: 1
Source: IEEE Xplore

ABSTRACT This paper analyzes the advantages and disadvantages of GA and BP algorithms, and presents the iteration of hybrid algorithm based on both algorithms. The hybrid algorithm incorporates the stronger global search of GA into the stronger local search of BP, and can search out the global optimum faster than each algorithm. At last, the hybrid algorithm is proved converge to the global optimum with the probability of 1.

0 0
 · 
0 Bookmarks
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

BP
 
BP algorithms
 
disadvantages
 
global optimum
 
hybrid algorithm
 
paper analyzes
 
presents
 
stronger global search
 
stronger local search