Patent Number: 6,167,390

Title: Facet classification neural network

Abstract: A classification neural network for piecewise linearly separating an input space to classify input patterns is described. The multilayered neural network comprises an input node, a plurality of difference nodes in a first layer, a minimum node, a plurality of perceptron nodes in a second layer and an output node. In operation, the input node broadcasts the input pattern to all of the difference nodes. The difference nodes, along with the minimum node, identify in which vornoi cell of the piecewise linear separation the input pattern lies. The difference node defining the vornoi cell localizes input pattern to a local coordinate space and sends it to a corresponding perceptron, which produces a class designator for the input pattern.

Inventors: Brady; Mark J. (Cottage Grove, MN), Million; Belayneh W. (St. Paul, MN), Strand; John T. (May Township, MN)

Assignee: 3M Innovative Properties Company

International Classification: G06K 9/64 (20060101); G06F 015/18 (); G06K 009/62 ()

Expiration Date: 12/26/2017