Abstract
Pattern Recognition is a process which recognizes a pattern using a machine or computer. Pattern recognition techniques are concerned with the theory and algorithms of putting abstract objects, e.g., measurements made on physical objects, into categories. Typically the categories are assumed to be known in advance, although there are techniques to learn the categories. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. In this paper neural network techniques and methods imported from statistical learning theory that has been receiving increasing attention is discussed which are at the forefront of the exciting and challenging field