Data processing: artificial intelligence – Neural network – Learning task
Patent
1997-11-13
2000-04-11
Hafiz, Tariq R.
Data processing: artificial intelligence
Neural network
Learning task
706 20, G06N 302, G06N 500
Patent
active
060497939
ABSTRACT:
A system for building an artificial neural network is provided which precisely defines the network's structure of artificial neurons, and non-iteratively determines the synapse-weights and hard limiter threshold of each artificial neuron of the network. The system includes a computer for analyzing input data, which represents patterns of different classes of signals, to generate one or more data points in two or three dimensions representative of the signals in each of the different classes. A distribution of the data points is visualized on a map on an output device coupled to the computer. The data points are clustered on the map into clusters in accordance with the classes associated with the data points, and the map is then partitioned into regions by defining linear boundaries between clusters. The artificial neural network is configured in accordance with the data points, clusters, boundaries, and regions, such that each boundary represents a different artificial neuron of the artificial neural network, and the geometric relationship of the regions on the map to the classes defines the logic connectivity of the artificial neurons. The synaptic weights and threshold of each artificial neuron in the network are graphically determined based on the data points of the map.
REFERENCES:
patent: 5005206 (1991-04-01), Naillon et al.
patent: 5019858 (1991-05-01), Suzuki et al.
patent: 5103488 (1992-04-01), Gemello et al.
patent: 5134396 (1992-07-01), Sirat et al.
patent: 5204718 (1993-04-01), Morita
patent: 5263097 (1993-11-01), Katz et al.
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5299284 (1994-03-01), Roy
patent: 5361201 (1994-11-01), Jost et al.
patent: 5361326 (1994-11-01), Aparicio IV
patent: 5420963 (1995-05-01), Kuwata
patent: 5438629 (1995-08-01), Moed et al.
patent: 5452399 (1995-09-01), Moed
patent: 5544256 (1996-08-01), Brecher et al.
patent: 5619593 (1997-04-01), Takamatsu et al.
patent: 5657487 (1997-08-01), Doner
patent: 5664067 (1997-09-01), Moed et al.
patent: 5796924 (1998-08-01), Errico et al.
patent: 5854993 (1999-03-01), Grichnik
G. S. Rogers, Matrix Derivatives, Marcel Dekker, Inc., "Examples of Optimization," pp. 93-100, 1980.
S.L. Campbell and C.D. Meyer, Jr., "Generalized Inverses of Linear Transformations", Dover Pub., Inc., pp. 8-15, 104-115, 1979.
P. Peretto, "An Introduction to the Modeling of Neural Networks", Cambridge University Press, pp. 230-249, 1992.
G. Barrie Wetherill, "Regression Analysis with Applications", Champman and Hall, pp. 10-13, 1986.
T. Kohonen, "Self Organization and Associative Memory", Berlin Heidelberg New York tokyo, 1984, pp. 14-21, pp. 178-188.
J. Bibby et al., "Prediction and Improved Estimation in Linear Models", John Wiley & Sons, pp. 6-9, pp. 75-81, 1977.
Frank Rosenblatt, "Principles of Neurodynamics", Spartan Books, pp. 78-151, 1959.
D.E. Rumelhart et al., Parallel Distributed Processing: Explorations i the Microstructures of Cognitition Learning internal representations by error propagation, vol. 1, MIT Press, pp. 318-362, 1980.
J. R. Magnus et al., "Matrix Differential Calculus with Applications in Statistics and Econometrics", John Wiley & Sons, pp. 32-39, 56-62, 130-143, 1988.
S. Amari, "Meural Theory of Association and concept-Formation", Biological Cybernetics, pp. 175-185, 1977.
S. Amari, Mathematics in Neural Networks, (1991) in Japanese.
E.B. Baum, "Neural Net Algorithms that Learn in Polynomial Time from Examples and Queries," IEEE Tran. on Neural Networks, vol. 2 (1), pp. 5-19, Jan. 1991.
E.B. Baum and K.J. Lang, "Constructing Hidden Units using Examples and Queries," Advances in Neural Information Processing Systems 3, Morgan Kaufmann Publishers, pp. 904-910, Dec. 1991.
Shin-Yee Lu, "Pattern Classification Using Self-Organiation Feature Maps", IEEE ICNN 1990.
Hafiz Tariq R.
Lukacher Kenneth J.
Pender Michael
LandOfFree
System for building an artificial neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System for building an artificial neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for building an artificial neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1184119