Patent · US Expired

Methods and apparatus for building a support vector machine classifier

US6327581A · kind A · utility

173Cited by
4References
50Claims
0Family size

Assignee

Inventor

Key dates

Filing dateApr 6, 1998
Grant dateDec 4, 2001
Priority date
Expiry dateApr 6, 2018

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/2411
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Solving a quadratic programming problem involved in training support vector machines by sweeping through a set of training examples, solving small sub-problems of the quadratic programming problem. Each of these sub-problems has an analytic solution, which is faster that the numerical quadratic programming solutions used in the prior art. In one embodiment, training examples with non-optimal Lagrange multipliers are adjusted, one at a time, until all are optimal (e.g. until all examples fulfill the Kuhn-Tucker conditions). In another embodiment, training examples with non-optimal Lagrange multipliers are paired and then adjusted, until all are optimal.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.