Perceptive system including a neural network

Details Perceptive system including a neural network Perceptive system including a neural network

1997-07-30

1998-11-10

Hafiz, Taric R.

Data processing: artificial intelligence

Neural network

Learning task

706 16, 706 25, 706 31, G06E 100, G06E 300

Patent

active

058359010

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. If clustering occurs, then a classification signal corresponding to the node is generated. However, if the input feature vector is not clustered to a declared node, then the second layer outputs a signal indicating novelty. The RTL neural network is used in a perceptive system which alternatively selects the RTL network novelty output or the output of a classifier trained on historical target data if the input vector is a subset of the historical target data.

REFERENCES:
patent: 3440617 (1969-04-01), Lesti
patent: 4912649 (1990-03-01), Wood
patent: 4912651 (1990-03-01), Wood et al.
patent: 4912652 (1990-03-01), Wood
patent: 4912654 (1990-03-01), Wood
patent: 4912655 (1990-03-01), Wood
patent: 5041976 (1991-08-01), Marko et al.
patent: 5080064 (1992-01-01), Buslepp et al.
patent: 5083541 (1992-01-01), Chen
patent: 5090388 (1992-02-01), Hamburg et al.
patent: 5093792 (1992-03-01), Taki et al.
patent: 5095443 (1992-03-01), Watanabe
patent: 5113483 (1992-05-01), Keeler et al.
patent: 5121467 (1992-06-01), Skeirik
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5384895 (1995-01-01), Rogers et al.
patent: 5438629 (1995-08-01), Moed et al.
Sin, S.-K. and R.J.P deFigueiredo. "A method for the design of evolutionary multilayer neural networks." IEEE Intl. Conf. on Neural Networks, Mar. 1993.
Whitehead, B.A. and T.D. Choate. "Evolving space-filling curves to distribute radial basis functions over an input space." IEEE Trans. on Neural Networks, Jan. 1994.
Larry Medsker and David Bailey."Integrating Expert Systems and Nenral Networks." IEEE/ACM Intl. Conf. on Developing & Managing Expert System Programs. Sep. 30-Oct. 2., 1991.
Confidential Demonstration of prototype system at Fort Drum, New York in May 1991.
Newspaper article, circa Dec. 1991-Feb. 1992, describing Oct. 1991 test of a Martin Marietta classifier system in Idaho.
Jan. 26, 1993 offer for sale of a system embodying features now claimed in the application.

Affiliated with

Also associated with

Rating

Perceptive system including a neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Perceptive system including a neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Perceptive system including a neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1528883