Pattern Classification Using Linear Programming

Abstract

The paper presents a new method for pattern classification that uses linear programming formulations. The method can generate neural network type networks to take advantage of parallel computation in the classification phase. Application of the technique to a wide variety of problems, including speech and image recognition, is being explored. INFORMS Journal on Computing, ISSN 1091-9856, was published as ORSA Journal on Computing from 1989 to 1995 under ISSN 0899-1499.