Patent
1993-06-30
1996-05-14
Downs, Robert W.
395 21, 395 23, 395 27, G06F 1518
Patent
active
055175970
ABSTRACT:
Based on the recognition that transfer functions of Boolean completeness can be expressed as a domain within a periodic function, an architecture of a artificial neuron which is fully generalized in application and capable of rapid learning with minimal memory requirements while maintaining content addressability of memory, is provided. Full functionality of this architecture is demonstrated for an input vector containing two values. Extension to three variables shows the potential for generality of this architecture to N-valued input vectors.
REFERENCES:
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4897814 (1990-01-01), Clark
patent: 4943931 (1990-07-01), Allen
patent: 4972363 (1990-11-01), Nguyen et al.
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5113367 (1992-05-01), Marrian et al.
patent: 5113507 (1992-05-01), Jaeckel
patent: 5148385 (1992-09-01), Frazier
patent: 5265224 (1993-11-01), Maruno
McClelland, et al., Explorations in Parallel Distributed Processing, MIT Press, 1988, 130-137.
Rosen, et al, "Transcendental Functions in Backward Error Propagation," 1990 IEEE Int'l. Conf. on Systems, Man and Cybernetics, 4-7 Nov. 1990, 239-241.
Lippmann, R. P., "An Introduction to Computing with Neural Nets," IEEE ASSP Mag., Apr. 1987, 4-22.
McClelland et al, Explorations in Parallel Distributed Processing, MIT Press, 1988, 83-108.
Hirose, et al, "Back-Propagation Algorithm Which Varies the Number of Hidden Units," Neural Networks, vol. 4(1), 1991, 61-66.
Tenorio, M., "Topology Synthesis Networks," Parallel Computing, 1990, 363-380.
Tsai, W. K., "ASDM A Novel Network Model," U. C. Irvine, IJCNN, 1990, 771-776, vol. I.
Jockusch, S., "A Neural Network Which Adapts," Parallel Processing in Neural Systems and Computers, 1990, 169-172.
Kulkarni, A. D., "Self Organizing Neural Networks with a Split/Merge Algorithm," ACM SIGSMALL/PC, 1990, 255-261.
Golea, M., "A Growth Algorithm for Neural Network Decision Trees," Europhysics Letters, 1990, 205-210.
Fahner, G., "A Higher Order Unit That Performs Arbitrary Boolean Functions," IJCNN, 1990, 193-197.
Barnden, J., "Dissolving Variables in Connectionist Combinatory Logic," Jan. 31, 1990, 709-714.
Tattersall, G. D., "Optimal Rule Induction in Neural Networks," INNC, 1990, 788.
Milotti, E., "Parity and the Shapes of Neuron Transfer Functions in Feedforward Neural Networks," Int'l. J. of Neural Systems, 1990, 247-248.
Sutherland, J. G., "A Holographic Model of Memory, Learning and Expression," Int'l. J. of Neural Systems, 1990, 259-267.
Loos, H., "Parity Modeline," IJCNN, 1990, 111-118.
Milligan, D., "Requirements for the Synthesis of Boolean Neural Networks," IJCNN, 1990, 567-572.
Deffuant, G., "Neural Units Recruitment Algorithm for Generation of Decision Trees," IJCNN, 1990, 637-642.
Martin, R., "Single-Interval Learning by Simile within a Simulated Hebbian Neural Network," Computers Math Applic., 1990, 213-225.
Stinchcombe, et al, "Universal Approximation Using Feedforward Networks with Non-Sigmoid Hidden Layer Activation Functions," IJCNN 1989, I-613 to I-617.
Aparicio, IV Manuel
Otto Samuel E.
Downs Robert W.
Duffield Edward
International Business Machines - Corporation
LandOfFree
Convolutional expert neural system (ConExNS) does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Convolutional expert neural system (ConExNS), we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convolutional expert neural system (ConExNS) will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1903544