SVM light

Publication	Joachims/97b: Text Categorization with Support Vector Machines: Learning with Many Relevant Features Joachims/98c: Making large-Scale SVM Learning Practical Joachims/99c: Transductive Inference for Text Classification using Support Vector Machines Vapnik/95a: The Nature of Statistical Learning Theory
Name	SVM light
Description	SVMlight is an implementation of Support Vector Machines (SVMs) in C. The main features of the program are the following:  fast optimization algorithm working set selection based on steepest feasible descent "shrinking" heuristic caching of kernel evaluations use of folding in the linear case includes algorithm for approximately training large transductive SVMs (TSVMs) can train SVMs with cost models handles many thousands of support vectors handles several ten-thousands of training examples supports standard kernel functions and lets you define your own uses sparse vector representation The source code is free for scientific use. Please follow the link "SVMlight - Details and Download". There is also a regression support vector machine based on SVMlight available: Please follow the link labeled "mySVM". Description SVMlight is an implementation of Vapnik's Support Vector Machine (see "The Nature of Statistical Learning Theory") for the problem of pattern recognition. The optimization algorithm used in SVMlight is described in "Making large-Scale SVM Learning Practical.". The algorithm has scalable memory requirements and can handle problems with many thousands of support vectors efficiently. This new version also includes a new algorithm for training large-scale transductive SVMs. The algorithm proceeds by solving a sequence of optimization problems lower-bounding the solution using a form of local search. The code has been used on a large range of problems, including text classification (see publications above), several image recognition tasks, and medical applications. Many tasks have the property of sparse instance vectors. This implementation makes use of this property which leads to a very compact and efficient representation.
Generalization	Support Vector Machine (SVM)
Method Type	System