Patent
1995-02-17
1998-02-17
Davis, George B.
395 11, G06F 1518
Patent
active
057200033
ABSTRACT:
A method and apparatus for determining the accuracy limit of a learning machine for predicting path performance degradation imposed by the quality of the path performance data is disclosed. A plurality of learning machines of increasing capacity are trained using training data and tested using test data, and the training error rates and test error rates are calculated. The asymptotic error rates of the learning machines are calculated and compared. When the change in asymptotic error rate falls below a certain rate, the asymptotic error rate estimates the accuracy limit for a learning machine for predicting path performance degradation. The accuracy limit is derived from insufficiencies in the path performance data and is applicable to any learning machine trained on and applied to the path performance data, regardless of the complexity of the learning machine or the size of the training data set.
REFERENCES:
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5563983 (1996-10-01), Nozaki et al.
patent: 5590218 (1996-12-01), Ornstein
Bos, S. et al., "Generalization Ability of Perceptions with Continuous Outputs," Physical Review E, vol. 47, No. 2, pp. 1384-1391, Feb. 1993.
Chiang, W.-P., Cortes, C., Jackel, L.D., LeCun, Y., and Lee, W., "Accuracy Limits of Machine Learning: Predicting Communication Path Degradation or Failure," Presented at Symposium on Intelligent Systems in Communications and Power, Puerto Rico, Feb. 21-23, 1994.
Cortes, C., "Prediction of Generalization Ability in Learning Machines," PhD Thesis, University of Rochester, NY, 1993.
Cortes, C., et al., "Learning Curves: Asymptotic Valuers and Rate of Convergence," Advances in Neural Information Processing Systems, vol. 6, Morgan Kaufman, 1994.
Fine, T.L., "Statistical Generalization and Learning," Technical Report EE577, Cornell University, Fall 1993.
Hornik, K., et al., "Multilayer Feedforward Networks Are Universal Approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
Kohonen, T., et al., "Statistical Pattern Recognition with Neural Networks: Benchmarking Studies," Proc. IEEE Int. Conf. on Neural Networks, ICNN-88, vol. 1, pp. I-61-I-68, 1988.
Murata, N., et al., "Learning Curves, Model Selection, and Complexity of Neural Networks," Advances in Neural Information Processing Systems, vol. 5, pp. 607-614, Morgan Kaufman, 1992.
Seung, H.S., et al., "Statistical Mechanics of Learning Form Examples," Physical Review A, vol. 45, No. 8, pp. 6056-6091, Apr. 15, 1992.
Marko et al, "Automotive Diagnostics Using Trainable Classifiers: Statistical Testing and Paradigm Selection", IJCNN, Jun. 1990.
Tishby et al, "Consistent Inference of Probabilities in Layered Networks: Predictions and Generalization", IEEE, ICNN 1989.
Simpson et al, "Classification of Enceratium Gran. In Neural Networks", IEEE Neural Network for Ocean Engineering, 1991.
Chiang Wan-Ping
Cortes Corinna
Jackel Lawrence David
Lee William
Davis George B.
Lucent Technologies - Inc.
LandOfFree
Method and apparatus for determining the accuracy limit of a lea 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 determining the accuracy limit of a lea, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for determining the accuracy limit of a lea will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1791020