Title :
Learning separations by Boolean combinations of half-spaces
Author :
Rao, Nageswara S V ; Oblow, E.M. ; Glover, Charles W.
Author_Institution :
Center for Eng. Syst. Adv. Res., Oak Ridge Nat. Lab., TN, USA
fDate :
7/1/1994 12:00:00 AM
Abstract :
Given two subsets S1 and S2 (not necessarily finite) of ℜd separable by a Boolean combination of learning half-spaces, the authors consider the problem of (in the sense of Valiant) the separation function from a finite set of examples, i.e., they produce with a high probability a function close to the actual separating function. The authors´ solution consists of a system of N perceptrons and a single consolidator which combines the outputs of the individual perceptrons; it is shown that an off-line version of this problem, where the examples are given in a batch, can be solved in time polynomial in the number of examples. The authors also provide an on-line learning algorithm that incrementally solves the problem by suitably training a system of N perceptrons much in the spirit of the classical perceptron learning algorithm
Keywords :
learning (artificial intelligence); neural nets; Boolean combinations; consolidator; learning half spaces; online learning algorithm; perceptrons; separation function; separations; Contracts; Fractals; Piecewise linear techniques; Polynomials; Power engineering and energy; Systems engineering and theory;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on