Neural network and learning method for linearly unseparable patt

Details Neural network and learning method for linearly unseparable patt Neural network and learning method for linearly unseparable patt

1995-02-10

1996-05-28

Downs, Robert W.

G06F 1518

Patent

active

055220150

ABSTRACT:
A neural network has an input layer, a hidden layer, and an output layer. The neural network includes a lower neural network model composed of hidden layer neurons and input layer neurons for learning a plurality of linearly separable patterns, and a higher neural network model composed of hidden layer neurons and output layer neurons for combining the linearly separable patterns into a linearly unseparable pattern.

REFERENCES:
patent: 4912647 (1990-03-01), Wood
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5265224 (1993-11-01), Maruno
A. D. McAulay, "Engineering design neural networks using split inversion learning," IEEE First Int'l. Conf. on Neural Networks, pp. IV-635 to IV-641.
S. Y. Kung and J. N. Hwang, "An Algebraic Projection Analysis for Optimal Hidden Units Size and Learning Rates in Back-Propagation Learning", IEEE Int'l. Conf. on Neural Networks, pp. l-363 to l-370.
E. B. Baum, "Neural Net Algorithms that Learn in Polynomial Time from Examples and Queries," IEEE Trans. on Neural Networks, vol. 2 (1), pp. 5-19.
"On Hidden Nodes for Neural Nets" by G. Mirchandani, IEEE Transactions on Circuits and Systems, May 1989, No. 5, pp. 661-664, New York.
"Conditions on Activation Functions of Hidden Units for Learning by Backpropagation", M. Arai et al, International Neural Network Conference, Jul. 1990, pp. 877-880.
"Training of a Neural Network for Pattern Classification Based on an Entropy Measure" by C. Koutsouger AS et al, IEEE International Conference of Neural Networks, Jul. 1988, pp. 247-254.
"The Piecewise Linear Neural Network: Training and Recognition", Y. H. Kong et al, I JCNN International Joint Conference on Neural Networks, vol. 3, Jun. 17 1990, San Diego, pp. 245-250.
"Neural Network Design Using Voronoi Diagrams: Preliminaries", Bose et al, IEEE, pp. 7-11, Jun. 1992.
"The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks", M. Frean, Neural Computation, vol. 2, pp. 198-209, 1990, Massachusetts Institute of Technology.
"Learning in Feedforward Layered Networks: The Tiling Algorithm", M. Mezard et al, Journal of Physics A: Math, Gen. vol. 22, pp. 2191-2203, 1989.
"Design Artificial Neural Network based on the Principle of Divide-and -Conquer", P. Lian, 6/11-14/1991, pp. 1319-1322.
"Characterizing the Error Function of a Neural Network", B. Moore et al, Dec. 31 1988, pp. 49-57.
"Solving Large-Scale Optimization Problems in Divide-and Conquer Neural Networks" Y. P. Simon Foo, Jun. 18-22 1987, pp. 507-511.
"Problem Decomposition and Subgoaling in Artificial Neural Networks", P. Liang, Nov. 4-7 1990, pp. 178-181.

Affiliated with

Also associated with

Rating

Neural network and learning method for linearly unseparable patt 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 network and learning method for linearly unseparable patt, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network and learning method for linearly unseparable patt will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-793964