Data processing: artificial intelligence – Neural network – Learning method
Patent
1995-10-06
2000-02-08
Downs, Robert W.
Data processing: artificial intelligence
Neural network
Learning method
G06F 1518
Patent
active
060236930
ABSTRACT:
A learning system is used in a data processing apparatus for learning an input pattern by obtaining an internal-state value necessary for realizing a desired data conversion by performing a pattern conversion defined by the internal-state value and calculating an output pattern corresponding to the input pattern. The learning system comprises a pattern presenting unit for presenting an input pattern group of the subject to be learned for pattern conversion, dividing the input pattern group of the subject to be learned into at least two sets, selecting one of the divided sets, presenting the input pattern group of the selected set to a pattern conversion unit and presenting an input pattern group belonging to all the sets presented up to the current point when the internal-state value to be converged is obtained in accordance with the presentation of the selected set, and an error value calculating unit for calculating an error value representing a magnitude of a non-consistency between an output pattern group outputted in accordance with the presentation and a teacher pattern group representing a pattern to be obtained by the output pattern group.
REFERENCES:
J.L. McClelland and D.E. Rumelhart, Explorations in Parallel Distributed Processing, MIT Press, pp. 137-141, Dec. 1988.
P. Ransil, "Neural Models and Learning Rules," Thirty-Third IEEE Computer Society Int'l. Conf., pp. 384-386, Mar. 1988.
D.L. Prados, "Capacity of a Neural Network," Electronics Letters, vol. 24, No. 8, pp. 454-455, Apr. 1988.
P.F. Castelaz, "Neural Networks in Defense Applications," IEEE Int'l. Conf. on Neural Networks, pp. II-473 to II-480, Jul. 1988.
J.S.J. Lee and J.C. Bezdek, "A Feature Projection Based Adaptive Pattern Recognition Network," IEEE Int'l. Conf. on Neural Networks, pp. I-497 to I-505, Jul. 1988.
M.B. Reid et al., "Rapid Training of Higher-order Neural Networks for Invariant Pattern Recognition," Int'l. Joint Conf. on Neural Networks, pp. I-689 to I-692, Jun. 1989.
F. Tsung and G.W. Cottrell, "A Sequential Adder Using Recurrent Networks," Int'l. Joint Conf. on Neural Networks, pp. II-133 to II-139, Jun. 1989.
N.K. Perugini and W.E. Engeler, "Neural Network Learning Time: Effects of Network and Training Set Size," Int'l. Joint Conf. on Neural Networks, pp. II-395 to II-401, Jun. 1989.
M. Kohle and F. Schonbauer, "Segregation Algorithm: Splitting the Training Set Improves Learning," Int'l. Joint Conf. on Neural Networks, p. II-627, Jun. 1989.
A.H. Kramer and A. Sangiovanni-Vincentelli, "Efficient Parallel Learning Algorithms for Neural Networks," from Advances in Neural Information Processing Systems I, Morgan Kaufmann Pub., pp. 40-48, Dec. 1989.
T.P. Vogl, et al., Accelarating The Convergence Of The Back-Propagation Method, Biological Cybernetics, 1988, Springer-Vering, pp. 257-263.
Smith et al, Calibration Of Neural Networks Using Genetic Algorithms, With Application To Optimal Path Planning; First Annual Workshop On Space Operations, Automation & Robotics (SOAR '87); Aug. 5-7, 1987; pp. 519-526.
A. Khotanzad et al., IEEE International Conference On Neural Networks, vol. 1, Jul 24, 1988, San Diego, CA, "Distortion Invariant Character Recognition by a Multi-layer Perceptron and Backpropagation Learning", pp. 625-632.
Tanaka, et al., Dec. 15, 1988, Application to the Determination of a Fault Section in an Electric System of a Neural Network.
J. Sklansky and G. Wassel, Pattern Classifiers and Trainable Machines, Springer-Verlag, pp. 25-26, Dec. 1981.
Nguyen, et al., "A New LMS-Based Algorithm for Rapid Adaptive Classification in Dynamic Environments: Theory and Preliminary Results," IEEE Int'l. Conf. on Neural Networks, Jul. 24-27, 1988, I-455-I-463.
Gorman, et al., "Learned Classification of Sonar Targets Using a Massively Parallel Network," IEEE Trans. on Acoustics, Speech, and Signal Proc. Jul. 1988, 1135-1140.
Huang, S., Supervised Learning with a Selective Update Strategy for Artificial Neural Networks, M.S. Thesis, Univ. of Notre Dame, Jul. 1988, 29-42, 53-67.
Huang, et al., "Back Propagation with Selective Updates," Twenty-Third Annual Conf. on Info. Sciences and Systems, Mar. 1989, 584-589.
IEEE First International Conference On Neural Networks, vol. 2, Jun. 21, 1987, San Diego, CA, "Exploration of Backward Error Propagation as a Self-Organizational Structure", Robert M. Kuczewski et al., pp. 89-96.
IEEE First International Conference On Neural Networks, vol. 2, Jun. 21, 1987, San Diego, CA, "Learning Phenomena in Layered Neural Networks", Bernard Widrow et al., pp. 411-430.
Neural Networks, vol. 1, No. 4, 1988, Oxford, GB, "Generalization of Backpropagation with Application to a Recurrent Gas Market Model", Paul J. Werbos, pp. 339-356.
Asakawa Kazuo
Kawamura Akira
Kimoto Takashi
Masuoka Ryusuke
Tanahashi Jun'ichi
Downs Robert W.
Fujitsu Limited
LandOfFree
Learning system for a data processing apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Learning system for a data processing apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning system for a data processing apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1688500