Unsupervised neural network classification with back propagation

Details Unsupervised neural network classification with back propagation Unsupervised neural network classification with back propagation

1995-06-07

1996-12-31

Mancuso, Joseph

Image analysis

Learning systems

Neural networks

395 23, G06K 962

Patent

active

055902189

ABSTRACT:
An unsupervised back propagation method for training neural networks. For a set of inputs, target outputs are assigned l's and O's randomly or arbitrarily for a small number of outputs. The learning process is initiated and the convergence of outputs towards targets is monitored. At intervals, the learning is paused, and the values for those targets for the outputs which are converging at a less than average rate, are changed (e.g., 0.fwdarw.1, or 1.fwdarw.0), and the learning is then resumed with the new targets. The process is continuously iterated and the outputs converge on a stable classification, thereby providing unsupervised back propagation. In a further embodiment, samples classified with the trained network may serve as the training sets for additional subdivisions to grow additional layers of a hierarchical classification tree which converges to indivisible branch tips. After training is completed, such a tree may be used to classify new unlabelled samples with high efficiency. In yet another embodiment, the unsupervised back propagation method of the present invention may be adapted to classify fuzzy sets.

REFERENCES:
patent: 5226092 (1993-07-01), Chen
patent: 5260871 (1993-11-01), Goldberg
patent: 5274714 (1993-12-01), Hutcheson et al.
patent: 5283838 (1994-02-01), Togawa et al.
International Search Report of PCT/US/9411803.
Ultrasonics, vol. 30, No. 5, 1992, Guildford GB, pp. 317-324; Damarla, "A self-learning neural net for ultrasonic signal analysis" see p. 317, left column, line 1-p. 320, left col., line 20; figures 1-2.
IEEE Transactions on Computers, vol. 40, No. 12, Dec. 1991, New York US pp. 1320-1336, LIN "Neural-network-based fuzzy logic control and decision system" see abstract, see p. 1325, left col., line 28-p. 1327-right col., line 37; figures 2-5.
Proceedings: Applications of Artificial Neural Networks 3, vol. 1709/1, 21 Apr. 1992, Orlando, USA pp. 174-181; Shen "Application of neural networks to hyper-spectral image analysis and interpretation"; see p. 176, line 14-p. 177, line 8; figure 2.
1991 IEEE International Joint Conference on Neural Networks, vol. 2, 18 Nov. 1991, Singapore pp. 1554-1559 Mills "Reinforcement learning using bavk-propagation as a building block" see the whole document.

Affiliated with

Also associated with

Rating

Unsupervised neural network classification with back propagation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Unsupervised neural network classification with back propagation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Unsupervised neural network classification with back propagation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1148090