1995-04-14
1997-11-11
MacDonald, Allen R.
395 211, 395 24, 395 267, 395 268, 395 21, 395 23, 395 24, G10L 506
Patent
active
056872860
ABSTRACT:
A neural network apparatus, and methods for training the neural network apparatus, for processing input information, supplied as a data array, for a prespecified application to indicate output categories characteristic of the processing for that application. In the invention, an input stage accepts the data array and converts it to a corresponding internal representation, and a data preprocessor analyzes the data array based on a plurality of feature attributes to generate a corresponding plurality of attribute measures. A neural network, comprising a plurality of interconnected neurons, processes the attribute measures to reach a neural state representative of corresponding category attributes; portions of the network are predefined to include a number of neurons and prespecified with a particular correspondence to the feature attributes to accept corresponding attribute measures for the data array, and portions of the network are prespecified with a particular correspondence to the category attributes. A data postprocessor indicates the category attributes by correlating the neural state with predefined category attribute measures, and an output stage combines the category measures in a prespecified manner to generate on output category for the input information.
REFERENCES:
patent: 4874963 (1989-10-01), Aispector
patent: 5212730 (1993-05-01), Wileatley et al.
patent: 5253328 (1993-10-01), Hartman
patent: 5285522 (1994-02-01), Mueller
patent: 5303328 (1994-04-01), Masui et al.
G. Yen et al., "Unlearning Algorithm in Associative Memories: The Eigenstructure Method," IEEE Int'l Symp. on Circuits and Systems, May 10-13, 1992, pp. 355-358.
G. Yen et al., "A Learning and Forgetting Algorithm in Associative Memories: The Eigenstructure Method," IEEE Trans. on Circuits and Systems, 39(4):212-25, Apr. 1992.
G. Yen et al., "A Learning and Forgetting Algorithm in Associative Memories: The Eigenstructure Method," Conf. on Control and Decision, Dec. 11-13, 1991, pp. 847-852.
A. Michel et al., :"Analysis and Synthesis of a Class of Discrete-Time Neural Networks Described on Hypercubes," IEEE Trans. on Neural Networks, 2(1):32-46, Jan. 1991.
C. Youn et al., "Continuous Unlearning in Neural Networks," Electronics Letters, 25(3):202-03, Feb. 2, 1989.
J. Bridle, "Speech Recognition: Statistical and Neural Information Processing Approaches," D. Touretzky, ed., Advances in Neural Information Processing I, pp. 796-801, 1989.
M. Fanty et al., "Spoken Letter Recognition," R. Lippmann et al., eds., Advances in Neural Information Processing Systems 3, pp. 220-226, 1991.
"Retrieval Properties of Neural Networks with Hierarchical Clustering":, M.A. Pires Idiart et al., J. Phys. A: Math. Gen. 24, L649-L658 (1991).
"Exponential Storage and Retrieval in Hierachical Neural Networks", C. Willcox, J., Phys. A: Math. Gen 22, 4707-4728 (1989).
"The Functional Logic of Cortical Connections", S. Zeki et al., Nature 355(22), 311-317 (Sep. 1988).
"Hierarchical Model of Memory and Memory Loss", J.P. Sutton et al., J. Phys. A: Math. Gen. 21, 4443-4454 (1988).
"A Coded Block Adaptive Neural Network System with a Radical-Partitioned Structure for Large-Volume Chinese Characters Recognition,", M.W. Mao et al., Neural Networks 5(5), 835-841 (Sep. 1992).
"Solving the Interconnection Problem with a Linked Assembly of Neural Networks", A.D.P. Green et al., IEEE Proceedings-F 138(1), 63-72 (Feb. 1991).
"Multiscale Optimization in Neural Nets", E. Mjolsness et al., IEEE Trans. on Neural Networks 2(2), 263-274 (Mar. 1991).
"Hierarchical Neural Networks for the Storage of Correlated Memories", V. Deshpande et al., J. Statistical Phys. 64(3/4), 755-779 (1991).
"Ordered' Spin Glass: A Hierarchical Memory Machine", V.S. Dotsenko, J. Phys. C: Solid State Phys. 18, L1017-L1022 (1985).
"Adaptive Mixtures of Local Experts", R.A. Jacobs et al., Neural Computation 3, 79-87 (1991).
"Ising Spin Neural Networks with Spatial Structure", A.C.C.. Coolen, North-Holland Future Generations Computer System 6, 121-130 (1990).
Collins Alphonso A.
MacDonald Allen R.
LandOfFree
Neural networks with subdivision does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural networks with subdivision, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural networks with subdivision will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1235603