Data processing: artificial intelligence – Neural network – Learning method
Reexamination Certificate
2006-07-18
2006-07-18
Knight, Anthony (Department: 2121)
Data processing: artificial intelligence
Neural network
Learning method
C706S014000, C706S039000
Reexamination Certificate
active
07080053
ABSTRACT:
A method for evolving appropriate connections among units in a neural network includes a) calculating weight changes at each existing connection and incipient connections between units for each training example; and b) determining a K ratio using the weight changes, wherein said K ratio comprises the weight change of existing connections, and wherein if the K ratio the weight change of incipient connections exceeds a threshold, further including b1) increasing a weight of the existing connection; b2) creating new connections at the incipient connections. The method further includes c) pruning weak connections between the units.
REFERENCES:
patent: 5452402 (1995-09-01), Sakiyama et al.
patent: 5588091 (1996-12-01), Alkon et al.
patent: 5627942 (1997-05-01), Nightingale et al.
patent: 5636326 (1997-06-01), Stork et al.
patent: 5649067 (1997-07-01), Gentric et al.
patent: 5751915 (1998-05-01), Werbos
patent: 6311172 (2001-10-01), Tresp et al.
patent: 6424961 (2002-07-01), Ayala
Karin E.D., “A Simple Procedure for Pruning Back-Propagation Trained Neural Networks”, IEEE Transactions on Neural Networks. vol. 1, No. 2, Jun. 1, 1990. pp. 239-242.
Khorasani, et al., “Structure Adaptation in Feed-Forward Neural Networks”, Neural Networks, 1994. IEEE World Congress on Computational Intelligence. 1994 IEEE International Conference on Orlando. FL USA Jun. 27-Jul. 2, 1994. New York, NY. pp. 1403-1408.
Russell Reed, “Pruning Algorithms—A Survey”, IEEE Transactions on Neural Networks, vol. 4, No. 5, Sep. 1, 1993 pp. 740-747.
Ji et al., “Network Synthesis through Data-Driven Growth and Decay”, Neural Networks. vol. 10, No. 6. Aug. 1, 1997, pp. 1133-1141.
Yasui et al., “Convergence Suppression and Divergence Facilitation: New Approach to Prune Hidden Layer and Weights of Feedforward Neural Networks”, 1995 IEEE International Symposium on Circuits and Systems (ISCAS), Seattle, WA, Apr. 30-May 3, 1995, New York IEEE, US vol. 1, Apr. 30, 1995, pp. 121-124.
Adams Paul
Cox Kingsley J. A.
Pinezich John D.
Datskovskiy Sergey
F. Chau & Associates LLC
Knight Anthony
Research Foundation of State University of New York
LandOfFree
Neural network device for evolving appropriate connections does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network device for evolving appropriate connections, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network device for evolving appropriate connections will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3546260