Paper Title:
Constraint Projection Adaptive Natural Gradient Online Algorithm for SVM
  Abstract

The training of Support Vector Machine (SVM) is an optimization problem of quadratic programming which can not be applied to the online training in real time applications or time-variant data source. The online algorithms proposed by other researchers have high computational complexity and slow training speed, which can not be well applied to the time-variant problems as well. In this paper the projection gradient and adaptive natural gradient is combined. The constraint projection adaptive natural gradient online algorithm for SVM is proposed. The computation complexity of the constraint projection adaptive natural gradient algorithm is . The learning performance is compared via prediction of the concentration of component A of Continuous Stirred Tank Reactor. The results of simulation demonstrate that the time taken by the constraint projection adaptive natural gradient online algorithm for SVM is far less than that of incremental algorithm, while keep higher prediction precision.

  Info
Periodical
Advanced Materials Research (Volumes 139-141)
Edited by
Liangchi Zhang, Chunliang Zhang and Tielin Shi
Pages
1692-1696
DOI
10.4028/www.scientific.net/AMR.139-141.1692
Citation
Z. H. Sun, "Constraint Projection Adaptive Natural Gradient Online Algorithm for SVM", Advanced Materials Research, Vols. 139-141, pp. 1692-1696, 2010
Online since
October 2010
Authors
Export
Price
$35.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Yan Ping He
Abstract:The adaptive noise cancellation system by LMS algorithm need not to know the prior knowledge of input speech signal and noise, and can carry...
453
Authors: Yan Ping He, Hai Dong Zhang
Chapter2: Material Science, Environment Science and Engineering
Abstract:The paper introduces the principle and structure of adaptive filter based on LMS algorithm, studies a design scheme of a single frequency...
299
Authors: Rui Mei Lian
Abstract:An amended LMS Newton algorithm is proposed which create the nonlinear functional relation of the step factor μ and the error signal e...
458
Authors: Cai Yun Wu
Chapter 1: Mechatronics
Abstract:This paper studies the speech enhancement technology. A Lyapunov function of the tracking error systems is defined, and the adaptive filter...
1670
Authors: Lu Jun Cui, Hui Chao Shang, Gang Zhang, Yong Li, Ze Xiang Zhao
Chapter 3: Control and Automation Systems
Abstract:The present work investigated the adaptive noise control system based on neural network. The structure and the characteristics of ANC...
236