DocumentCode
3419751
Title
The research of learning algorithm of synergetic neural network
Author
Lu, Bin ; Tian, Yuru
Author_Institution
Sch. of Control & Comput. Eng., North China Electr. Power Univ., Baoding, China
fYear
2012
fDate
24-26 Aug. 2012
Firstpage
1308
Lastpage
1310
Abstract
Due to existing wide consistency between synergetic thought and neural network in associative memory, learning and pattern recognition, a new network called synergetic neural network arises at the historic moment which is different form the design method of traditional neural network .In the synergetic neural network, learn also is the study of weight matrix in a given training sample set. It´s learning problems can be summed up in how to evaluate the adjoint vector and prototype vector. Learning algorithm of synergetic neural network has a lot of kinds, each one has its unique advantages and disadvantages, On the basis of introduces the principle of the synergetic neural network ,this paper analyzed the selection of prototype pattern and the solving of adjoint vector. Finally analysis the advantages of learning algorithm of synergetic neural network based on cluster algorithm.
Keywords
learning (artificial intelligence); matrix algebra; neural nets; pattern clustering; vectors; adjoint vector; associative memory; cluster algorithm; learning algorithm; pattern recognition; prototype pattern selection; prototype vector; synergetic neural network; synergetic thought; weight matrix; cluster; synergetic Theory; synergetic learning algorithm; synergetic neural network;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science and Information Processing (CSIP), 2012 International Conference on
Conference_Location
Xi´an, Shaanxi
Print_ISBN
978-1-4673-1410-7
Type
conf
DOI
10.1109/CSIP.2012.6309102
Filename
6309102
Link To Document