Learning method for a data processing system having a multi-laye

Details Learning method for a data processing system having a multi-laye Learning method for a data processing system having a multi-laye

1991-04-23

1993-08-24

Fleming, Michael R.

Image analysis

Histogram processing

For setting a threshold

395 22, 382 10, G06F 1518

Patent

active

052396193

ABSTRACT:
A learning method for a neural network having at least an input neuron layer, an output neuron layer, and a middle neuron layer between the input and output layers. Each of the layers include a plurality of neurons which are coupled to corresponding neurons in adjacent neural layers. The learning method performs a learning function on the neurons of the middle layer on the basis of the respective outputs, or "ignition patterns", of the neurons in the neural layers adjacent to the middle layer. The ignition pattern of neurons in the input layer is decided artificially according to a preferable image pattern to be input. The ignition pattern of neurons in the output layer is decided artificially according to the ignition pattern of the input layer neurons, wherein the ignition pattern of the output layer neurons is predetermined to correspond to a code or pattern preferable for a user. The ignition pattern of the middle layer neurons, coupled to the associated neurons of the respective input and output layers, is then decided according to the ignition pattern of the input layer and the output layer.

REFERENCES:
patent: 4874963 (1989-10-01), Alspector
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5041916 (1991-08-01), Yoshida et al.
Graf et al., "VLSI Implementation of a Neural Network Model", Computer, Mar. 1988, 41-49.
Shepanski, J. F., "Fast Learning in Artificial Neural Systems: Multilayer Perception Training Using Optimal Estimation", IEEE Intl. Conf. on Neural Networks, Jul. 1988, I-465-472.
Lippmann, R. P., "Pattern Classification Using Neural Networks", IEEE Communications Mag., Nov. 1989, pp. 47-64.
Collins, J. W., "A Neural Network Based on Co-Occurrence Probabilities", IEEE First Intl. Conf. on Neural Networks, Jun. 1987, II-487--494.
Ramacher et al., "A Geometrical Approach to Neural Network Design", Intl. Joint Conf. Neural Networks, 1989, II-147-153.
Hecht-Neilsen, "Kolmogorov's Mapping Neural Network Existence Theorem", Maureen Caudill and Charles Butler: IEEE First International Conference on Neural Networks San Diego, California, Jun. 21-24, 1987, vol. III, The Institute of Electrical and Electronics Engineers, Inc., pp. III-IIb to III-14.

Affiliated with

Also associated with

Rating

Learning method for a data processing system having a multi-laye does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Learning method for a data processing system having a multi-laye, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning method for a data processing system having a multi-laye will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-835423