Hal Beck Phones & Addresses
-
Oakland, CA
-
Sacramento, CA
-
3825 Sequoyah Ave, Knoxville, TN 37919 (865) 637-7277
-
198 Pine St, Auburn, CA 95603 (530) 885-2896
-
San Diego, CA
-
Fort Worth, TX
Publications
Us Patents
Perceptive System Including A Neural Network
View pageUS Patent:
58359010, Nov 10, 1998
Filed:
Jul 30, 1997
Appl. No.:
8/903345
Inventors:
Herbert Duvoisin - Orlando FL
Hal E. Beck - Knoxville TN
Joe R. Brown - Austin TX
Mark Bower - Winder Park FL
Hal E. Beck - Knoxville TN
Joe R. Brown - Austin TX
Mark Bower - Winder Park FL
Assignee:
Martin Marietta Corporation - Bethesda MD
International Classification:
G06E 100
G06E 300
G06E 300
US Classification:
706 19
Abstract:
A real-time learning (RTL) neural network is capable of indicating when an input feature vector is novel with respect to feature vectors contained within its training data set, and is capable of learning to generate a correct response to a new data vector while maintaining correct responses to previously learned data vectors without requiring that the neural network be retrained on the previously learned data. The neural network has a sensor for inputting a feature vector, a first layer and a second layer. The feature vector is supplied to the first layer which may have one or more declared and unused nodes. During training, the input feature vector is clustered to a declared node only if it lies within a hypervolume defined by the declared node's automatically selectable reject radius, else the input feature vector is clustered to an unused node. Clustering in overlapping hypervolumes is determined by a decision surface. During testing of the RTL network, the same strategy is applied to cluster an input feature vector to declared (existing) nodes.