Efficient implementation of SVM for large class problems

Multiclass classification is an important problem in pattern recognition. Hierarchical SVM classifiers such as DAG-SVM and BHC-SVM are popular in solving multiclass problems. However, a bottleneck with these approaches is the number of component classifiers, and the associated time and space require...

Full description

Saved in:
Bibliographic Details
Main Authors: Ilayaraja, P., Neeba, N.V., Jawahar, C.V.
Format: Conference Proceeding
Language:English
Subjects:
Computational complexity
Data structures
Information technology
Lagrangian functions
Pattern recognition
Space technology
Support vector machine classification
Support vector machines
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multiclass classification is an important problem in pattern recognition. Hierarchical SVM classifiers such as DAG-SVM and BHC-SVM are popular in solving multiclass problems. However, a bottleneck with these approaches is the number of component classifiers, and the associated time and space requirements. In this paper, we describe a simple, yet effective method for efficiently storing support vectors that exploits the redundancies in them across the classifiers to obtain significant reduction in storage and computational requirements. We also present our extension to an algebraic exact simplification method for simplifying hierarchical classifier solutions.
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761231