Title :
The theoretical analysis of kernel technique and its applications
Author :
Tao, Qing ; Wang, Jiaqi ; Wu, Gaowei ; Wang, Jue
Author_Institution :
Inst. of Autom., Acad. Sinica, Beijing, China
fDate :
6/24/1905 12:00:00 AM
Abstract :
Investigates linear separability in feature space from Tietze extension theorem and function approximation theory, and kernel technique is motivated theoretically. Two kernel-based algorithms are presented. One of them is a general learning algorithm for feedforward neural networks, and they can solve large-scale classification problems
Keywords :
feedforward neural nets; function approximation; learning (artificial intelligence); learning automata; pattern classification; quadratic programming; radial basis function networks; Schauder basis; Tietze extension theorem; feature mappings; feedforward neural networks; function approximation theory; general learning algorithm; kernel covering approach; kernel mappings; kernel technique; large-scale classification problems; linear separability; support vectors; Approximation methods; Automation; Feedforward neural networks; Function approximation; Kernel; Large-scale systems; Neural networks; Projection algorithms; Support vector machine classification; Support vector machines;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005535
