Support vector machines

TLDR

Support Vector Machines offer theoretical advantages from computational learning theory while delivering strong performance on real‑world tasks such as text categorization and face detection. This collection of essays aims to acquaint readers with SVMs and provide practical guidance for their use. John Platt presents a practical guide and an efficient implementation technique for SVMs. SVMs achieve state‑of‑the‑art results on Reuters text categorization and strong performance on face detection.

Abstract

My first exposure to Support Vector Machines came this spring when heard Sue Dumais present impressive results on text categorization using this analysis technique. This issue's collection of essays should help familiarize our readers with this interesting new racehorse in the Machine Learning stable. Bernhard Scholkopf, in an introductory overview, points out that a particular advantage of SVMs over other learning algorithms is that it can be analyzed theoretically using concepts from computational learning theory, and at the same time can achieve good performance when applied to real problems. Examples of these real-world applications are provided by Sue Dumais, who describes the aforementioned text-categorization problem, yielding the best results to date on the Reuters collection, and Edgar Osuna, who presents strong results on application to face detection. Our fourth author, John Platt, gives us a practical guide and a new technique for implementing the algorithm efficiently.