Title :
Hidden space support vector machines
Author :
Zhang, Li ; Zhou, Weida ; Jiao, Licheng
Author_Institution :
Key Lab. for Radar Signal Process., Xidian Univ., Xi´´an, China
Abstract :
Hidden space support vector machines (HSSVMs) are presented in this paper. The input patterns are mapped into a high-dimensional hidden space by a set of hidden nonlinear functions and then the structural risk is introduced into the hidden space to construct HSSVMs. Moreover, the conditions for the nonlinear kernel function in HSSVMs are more relaxed, and even differentiability is not required. Compared with support vector machines (SVMs), HSSVMs can adopt more kinds of kernel functions because the positive definite property of the kernel function is not a necessary condition. The performance of HSSVMs for pattern recognition and regression estimation is also analyzed. Experiments on artificial and real-world domains confirm the feasibility and the validity of our algorithms.
Keywords :
nonlinear functions; pattern recognition; regression analysis; support vector machines; hidden nonlinear functions; hidden space support vector machines; high-dimensional hidden space; kernel functions; pattern recognition; regression estimation; Artificial neural networks; Fuzzy control; Kernel; Machine learning; Multilayer perceptrons; Pattern analysis; Pattern recognition; Quadratic programming; Radar signal processing; Support vector machines; Artificial neural networks (ANNs); pattern recognition; regression estimation; structural risk; support vector machines; Algorithms; Artificial Intelligence; Computer Simulation; Computing Methodologies; Decision Support Techniques; Feedback; Logistic Models; Neural Networks (Computer); Nonlinear Dynamics; Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2004.831161
