Method and apparatus for adaptive classification

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 27, G06F 1518

Patent

active

054795745

ABSTRACT:
A neural network and method for pipeline operation within a neural network which permits rapid classification of input vectors provided thereto is disclosed. In a training mode, a plurality of training input features are presented to the neural network and distances between the plurality of training features and a plurality of prototype weight values are concurrently computed. In response to an indication of a last training epoch count values for each of the prototype weight values are stored in a memory to thereby allow the neural network to operate in a probabilistic classification mode.

REFERENCES:
patent: 3601811 (1968-12-01), Yoshino
patent: 3638196 (1972-01-01), Nishiyama et al.
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4044243 (1977-08-01), Cooper et al.
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4319331 (1982-03-01), Elbaum et al.
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4660166 (1987-04-01), Hopfield
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4866645 (1989-09-01), Lish
patent: 4876731 (1989-10-01), Loris et al.
patent: 4893333 (1990-01-01), Baran et al.
patent: 4897811 (1990-01-01), Scofield
patent: 4904881 (1990-02-01), Castro
patent: 4906865 (1990-03-01), Holler
patent: 4920426 (1990-04-01), Hatori et al.
patent: 4937872 (1990-06-01), Hopfield et al.
patent: 4950917 (1990-08-01), Holler et al.
patent: 4956564 (1990-09-01), Holler et al.
patent: 4958375 (1990-09-01), Reilly et al.
patent: 4961002 (1990-10-01), Tam et al.
patent: 4994982 (1991-02-01), Duranton et al.
patent: 4999525 (1991-03-01), Park et al.
patent: 5003360 (1991-03-01), Okada et al.
patent: 5004932 (1991-04-01), Nejime
patent: 5010512 (1991-04-01), Hartstein et al.
patent: 5014096 (1991-05-01), Matsuda et al.
patent: 5014219 (1991-05-01), White
patent: 5021693 (1991-06-01), Shima
patent: 5021988 (1991-06-01), Mashiko
patent: 5028810 (1991-07-01), Castro et al.
patent: 5028969 (1991-07-01), Kashara et al.
patent: 5031154 (1991-07-01), Watanabe
patent: 5039870 (1991-08-01), Engeler
patent: 5039871 (1991-08-01), Engeler
patent: 5039941 (1991-08-01), Castro
patent: 5040134 (1991-08-01), Park
patent: 5045713 (1991-09-01), Shima
patent: 5054093 (1991-10-01), Cooper et al.
patent: 5055897 (1991-10-01), Canepa
patent: 5060278 (1991-10-01), Fukumizu
patent: 5063521 (1991-11-01), Peterson et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5075869 (1991-12-01), Holler et al.
patent: 5077677 (1991-12-01), Hurphy et al.
patent: 5083285 (1992-01-01), Shima et al.
patent: 5087826 (1992-02-01), Holler et al.
patent: 5095443 (1992-03-01), Watanabe
patent: 5095457 (1992-03-01), Jeong
patent: 5103405 (1992-04-01), Murphy et al.
patent: 5129038 (1992-07-01), Kohda et al.
patent: 5136176 (1992-08-01), Castro
patent: 5136177 (1992-08-01), Castro
patent: 5136178 (1992-08-01), Castro
patent: 5140538 (1992-08-01), Bass et al.
patent: 5142666 (1992-08-01), Yoshizawa et al.
patent: 5146542 (1992-09-01), Engeler
patent: 5146602 (1992-09-01), Holler et al.
patent: 5148514 (1992-09-01), Arima et al.
patent: 5151874 (1992-09-01), Jeong et al.
patent: 5151970 (1992-09-01), Engeler
patent: 5151971 (1992-09-01), Jousselin et al.
patent: 5155377 (1992-10-01), Castro
patent: 5157275 (1992-10-01), Stork et al.
patent: 5165009 (1992-11-01), Watanabe et al.
patent: 5165010 (1992-11-01), Masuda et al.
patent: 5166539 (1992-11-01), Uchimura et al.
patent: 5166938 (1992-11-01), Chung
patent: 5167006 (1992-11-01), Furuta et al.
patent: 5167008 (1992-11-01), Engeler
patent: 5168551 (1992-12-01), Jeong
patent: 5175793 (1992-12-01), Sakamoto et al.
patent: 5175858 (1992-12-01), Hammerstrom
patent: 5177746 (1993-01-01), Chung
patent: 5179596 (1993-01-01), Weingard
patent: 5187581 (1993-02-01), Kamatani
patent: 5187680 (1993-02-01), Engeler
patent: 5191637 (1993-03-01), Furuta et al.
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5222193 (1993-06-01), Brooks et al.
patent: 5237210 (1993-08-01), Castro
patent: 5247206 (1993-09-01), Castro
patent: 5247606 (1993-09-01), Tam
patent: 5255346 (1993-10-01), Wu et al.
patent: 5256911 (1993-10-01), Holler et al.
patent: 5264734 (1993-11-01), Holler et al.
patent: 5268320 (1993-12-01), Holler et al.
patent: 5276772 (1994-01-01), Wang et al.
patent: 5293454 (1994-03-01), Kamiya
D. F. Specht, "Probabilistic Neural Network for Classification, Mapping, or Associative Memory," IEEE Int'l. Conf. on Neural Networks, Jul. 1988, pp. I-525-I-532.
Chin S. Park, et al. U. S. Patent Application for Distance Calculating Neural Network Classifier Chip and System, Date of Deposit Jul. 1, 1993, total pages 108.
Hernan A. Castro, U. S. Patent Application for Neural Network Employing Absolute Value Calculating Synapse, Date of Deposit May 19, 1992, total pages 16.
Daniel Seligson, U. S. Patent Application for Neural Network Incorporating Difference Neurons, Date of Deposit Apr. 29, 1991, total pages 42.
Daniel Seligson, U. S. Patent Application for Neural Cells and Networks with Multiplexed Synapses, Date of Deposit Dec. 6, 1991, total pages 22.
C. L. Scofield, "Unsupervised Learning in the N-Dimensional Coulomb Network", (Abstract Only), Sep., 1988.
C. L. Scofield, "A Mean Field Theory of Layer IV of Visual Cortex and Its Application to Artificial Neural Networks", 1988.
M. Glier, "Artificial Neural Network VLSI Chip Development" Apr. 2, 1992, pp. 1-30.
"Ni1000 Adaptive Classifier, Preliminary Target Specification", Aug. 26, 1992, pp. 1-1 through 5-12.
C. Park, "Ni1000 Micro-Controller Design Review", Jun. 25, 1992.
D. L. Reilly, L. N. Cooper, C. Elbaum, "A Neural Model for Category Learning," Biological Cybernetics, 1982, pp. 35-41.
C. M. Bachman, L. N. Cooper, A Dembo, O. Zeitouni, "A Relaxation Model for Memory with High Density Storage," Proc. Natl. Acad. Sci. USA 21, Nov., 1987.
D. L. Reilly, C. Scofield, C. Elbaum, L. N. Cooper, "Learning System Architectures Composed of Multiple Learning Modules," IEEE First Int'l Conf. on Neural Networks, Jun. 1987, pp. 495-503.
C. L. Scofield, D. L. Reilly, C. Elbaum, L. N. Cooper, "Pattern Class Degeneracy In An Unrestricted Storage Density Memory," 1987.
R. Rimey, P. Gouin, C. Scofield, D. L. Reilly, "Real-time 3-D Object Classification Using A Learning System", Intelligent Robots and Computer Vision, Oct., 1986, pp. 552-557.
D. L. Reilly, C. Scofield, P. R. Gouin, R. Rimey, E. A. Collins, S. Ghosh, "An Application of a Multiple Neural Network Learning System to Industrial Part Inspection," 1988, pp. 1-14.
E. Collins, S. Shosh, C. L. Scofield, "An Application of a Multiple Neural Network Learning System to Emulation of Mortgage Underwriting Judgements," Jul., 1988.
C. L. Scofield, "Learning Internal Representations in the Coulomb Energy Network," Jun., 1987.
D. L. Reilly, L. N. Cooper, "An Overview of Neural Networks: Early Models to Real World Systems," An introduction to Neural and Electronic Networks, 1990, pp. 227-247.
P. D. Zemany, D. Reilly, E. C. Real, D. P. Morgan, L. Riek, C. S. Scofield, et al., "Experiments in Discrete Utterance Recognition using Neural Networks," Feb., 1989, pp. 1-2.
D. P. Morgan, C. L. Scofield, T. M. Lorenzo, E. C. Real, D. P. Loconto, "A Keyword Spotter Which Incorporates Neural Networks for Secondary Processing," Apr., 1990.
D. L. Reilly, E. Collins, C. L. Scofield, S. Ghosh, P. Stefancyk, "Risk Assessment of Mortgage Applications with as Neural Network System: An Update as the Test Portfolio Ages," IJCNN, Jan., 1990.
David W. Tank and John J. Hopfield, "Collective Computation in Neuronlike Circuits", Scientific American, Dec., 1987, pp. 104-114.
Commercial Applications of the Nestor Learning System, 1989, pp. 1-28.
Learning Systems Based on Multiple Neural Networks, 1988, pp. 1-14.
C. L. Scofield and Douglas L. Reilly, "Into Silicon: Real Time Learning in a High Density RBF Neural Network". Jul., 1991.
D. P. Morgan, C. L. Scofield, J. E. Adock, "Multiple Neural Network Topologies Applied to Keyword Spotting". May, 1991.
C. L. Scofield, L. Kenton, J. Chang, "Multiple Neural Net Architectures for Character Recognition", Feb., 1991.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method and apparatus for adaptive classification does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for adaptive classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for adaptive classification will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1375708

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.