N-tuple or RAM based neural network classification system...

Details N-tuple or RAM based neural network classification system... N-tuple or RAM based neural network classification system...

2006-02-14

2006-02-14

Knight, Anthony (Department: 2121)

Data processing: artificial intelligence

Machine learning

C706S015000, C706S020000

Reexamination Certificate

active

06999950

ABSTRACT:
The invention relates to n-tuple or RAM based neural network classification methods and systems and, more particularly, to n-tuple or RAM based classification systems where the decision criteria applied to obtain the output sources and compare these output sources to obtain a classification are determined during a training process. Accordingly, the invention relates to a system and a method of training a computer classification system which can be defined by a network comprising a number of n-tuples or Look Up Tables (LUTs), with each n-tuple or LUT comprising a number of rows corresponding to at least a subset of possible classes and comprising columns being addressed by signals or elements of sampled training input data examples.

REFERENCES:
patent: 4975975 (1990-12-01), Filipski
patent: 5359699 (1994-10-01), Tong et al.
patent: 5555344 (1996-09-01), Zūnkler
patent: 5790754 (1998-08-01), Mozer et al.
patent: 5893058 (1999-04-01), Kosaka
patent: 6021387 (2000-02-01), Mozer et al.
patent: 6169981 (2001-01-01), Werbos
patent: 6238342 (2001-05-01), Feleppa et al.
patent: 6571227 (2003-05-01), Agrafiotis et al.
patent: 0935212 (1999-08-01), None
patent: 9200572 (1992-01-01), None
Jorgensen et al., “Theoretical Analysis and Improved Decision Criteria for the n-Tuple Classifier”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, No. 4, Apr. 1999.
Jorgensen et al., “Boosting the Performance of Weightless Neural Networks by Using a Post-Processing Transformation of the Output Scores”, International Joint Conference on Neural Networks, Jul. 1999, vol. 2, pp. 812-816.
Simoes et al., “The Adaptive Weight Using RAM”, 1997 International Conference on Systems, Man and Cybernetics, Oct. 1997, vol. 5, pp. 4053-4056.
Lucas et al., “Recognition of Chain-Coded Handwritten Character Images With Scanning n-Tuple Method”, Electronic Letters, Nov. 1995, vol. 34, No. 24.
Jung et al., “Joint Feature and Classifier Design for OCR”, Proceedings of the 3rdInternational Conference on Document Analysis and Recognition, Aug. 1995, vol. 2, pp. 1115-1118.
Allinson et al., “Neurons, N-Tuples and Faces”, Computing and Control Engineering Journal, Jul. 1990.
Lucas et al., “Statistical Syntactic Methods for High-Performance OCR”, IEE Proceedings-Visual Image Signal Process, Feb. 1996, vol. 143, No. 1.
Lucas, S., “Rapid Content-Based Retrieval from Document Image Databases”, IEEE Colloquium on Intelligent Image Databases, May 1996.
Bradshaw et al., “Improving the Generalisation of the N-Tuple Classifier Using the Effective VC Dimension”, Electronics Letters Sep. 1996, vol. 32, No. 20.
Lucas, S., “Can Scanning N-Tuple Classifiers be Improved by Pre-transforming Training Data?”, IEE Workshop on Handwriting Analysis and Recognition-A European Perspective, May 1996.
Lucas, S., “Continuous N-Tuple Classifier and Its Application to Face Recognition”, Electronic Letters, Sep. 1997, vol. 33, No. 20.
Jorgensen et al., “Nonlinear Noise Filtering and Texture Recognition by an Optoelectronic Neural Network That Implements a Mean Field Annealing Algorithm”, Proceedings of the 1993 International Joint Conference on Neural Networks.
Jorgensen, T., “A RAM-based Neural Net with Inhibitory Weights and its Application to Recognising Handwritten Digits”, International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing, Aug. 1996.
Jung et al., “N-Tuple Features for OCR Revisited”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Jul. 1996, vol. 18, No. 7.
Allinson et al., “A Principled Approach to N-Tuple Recognition Systems”, IEE Colloquium on Pattern Recognition, Feb. 1997.
Linneberg et al., “Towards Semen Quality Assessment Using Neural Networks”, Proceedings of the 1994 IEEE Workshop on Neural Networks for Signal Processing, Sep. 1994, pp. 509-517.
Linneberg et al., “Discretization Methods for Encoding of Continuous Input Variables for Boolean Neural Networks”, Internation Joint Conference on Neural Networks, Jul. 1999, vol. 2, pp. 1219-1224.
Kolcz et al., “Application fo the CMAC Input Encoding Scheme in the N-Tuple Approximation Network”, IEE Proceedings-Computers and Digital Techniques, May 1994, vol. 141, Iss 3.
Bishop et al., “Auto-Associative Memory Using N-Tuple Techniques”, Intelligent Systems Engineering, Winter 1994.
Rohwer, R., “Two Bayesian Treatments of the N-Tuple Recognition Method”, Artificial Neural Networks, Jun. 1995.
Duslim et al., “P Pattern Recognition Based on a Probablistic RAM Net Using N-Tuple Input Mapping”, IEE Proceedings-Vision Image and Signal Processing, Dec. 1998, vol. 145, Iss 6.
Guoqing et al., “A Novel Adaptive Pattern Recognition Model with Sparse Associative Memory Networks”, 1991 IEEE International Joint Conference on Neural Networks, Nov. 1991, vol. 1, pp. 272-280.
Williams et al., “Hardware Implementation of RAM-Based Neural Networks for Tomographic Data Processing”, IEE Proceedings-Computers and Digital Techniques, Mar. 1999, vol. 146, Iss 2.
Austin, Jr., “A Review of RAM Based Neural Networks”, Proceedings of the 4thInternational Conference on Microelectronics for Neural Networks and Fuzzy Systems, Sep. 1994.
Bledsoe, W.W. and Browning, I., 1959. Pattern Recognition and Reading by Machine.Proceedings of the Eastern Joint Computer Conference.pp. 225-232.
Morciniec, M. and Rohwer, R., 1996. A Theoretical and Experimental Account of n-tuple Classifier Performance.Neural Comp.,pp. 629-642.
T.M. Jorgensen, S.S. Christensen, and C. Liisberg. Cross-validation and information measures for RAM based neural networks. RAM-based neural networks. J. Austin, ed., World Scientific, London, pp. 78-88, 1998.
Jorgensen, T.M. Classification of handwritten digits using a ram neural net architecture.International Journal of Neural Systems.vol. 8, No. 1 (Feb. 1997) 17-25.
Jorgensen, T.M., Linneberg, C. Theoretical Analysis and Improved Decision Criteria for the n-Tuple Classifier.IEEE Transactions on pattern analysis and machine intelligence.vol. 21, No. 4, Apr. 1999.
EP 0 935 212 A1 Intellix A/S.
WO 92/00572 University College London.
Jorgensen et al, IEEE Transactions on Pattern Analysis & Machine, vol. 10, No. 4, Apr. 1999.
Jorgensen, International Journal of Neural Systems, vol. 8, No. 1, p. 17-p. 25 Feb. 1997.

Affiliated with

Also associated with

Rating

N-tuple or RAM based neural network classification system... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with N-tuple or RAM based neural network classification system..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and N-tuple or RAM based neural network classification system... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3641000