Research on multi-degree-of-freedom neurons with weighted graphs

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

zhangdi于2010-03-29批量导入

zhangdi于2010-03-29批量导入

Univ Electr Sci & Technol China.; Chinese Univ Hong Kong.; Asia Pacific Neural Network Assembly.; European Neural Network Soc.; IEEE Circuits & Syst Soc.; IEEE Computat Intelligence Soc.; Int Neural Network Soc.; Natl Nat Sci Fdn China.; KC Wong Educ Fdn Hong Kong.

Chinese Acad Sci, Inst Semicond, Artificial Neural Networks Lab, Beijing 100083, Peoples R China; Zhejiang Univ Technol, Informat Engn Coll, Inst Intelligent Informat Syst, Hangzhou 310032, Peoples R China

Univ Electr Sci & Technol China.; Chinese Univ Hong Kong.; Asia Pacific Neural Network Assembly.; European Neural Network Soc.; IEEE Circuits & Syst Soc.; IEEE Computat Intelligence Soc.; Int Neural Network Soc.; Natl Nat Sci Fdn China.; KC Wong Educ Fdn Hong Kong.