Learning method for a data processing system

Details Learning method for a data processing system Learning method for a data processing system

1993-05-07

1995-07-04

Downs, Robert W.

G06F 1518

Patent

active

054308291

ABSTRACT:
A learning method for a data processing system comprising an input layer and an output layer which comprise a plurality of neurons, each of which outputs predetermined data after activating according to the predetermined processing results performed onto an input data. A middle layer is arranged between the input and output layer, the middle layer comprising a plurality of neurons each of which is connected to each neuron of the input and output layer. The activation patterns of the input layer and the output layer are determined arbitrarily according to a plurality of inputs and outputs. Weights of synapses of the middle layer and the output layer are increased so as to obtain the tendency that the activation pattern of the middle layer becomes the nearest approximation to the activation patterns of the input layer and the output layer according to each input and output. This method is performed with respect to all inputs and outputs.

REFERENCES:
patent: 4874963 (1989-10-01), Alspector
patent: 5033006 (1991-07-01), Ishizuka et al.
Rumelhart et al, "Learning Internal Representations by Error Progagation", Parallel Distribution Processing, vol. 1, Foundation, Rumelhart et al, MIT Press, 1986, pp. 318-362.
Lippmann, R. P., "An Introduction to Computing with Neural Nets,"IEEE ASSP Magazine, Apr. 1987, 4-20.
IEEE International Conference on Neural Networks, Shpanski "Fast Learning In Artificial Neural Systems: Multilayer Perceptron Training Using Optimal Estimation", vol. 1, Jul. 1988, pp. 465-472.
IEEE First International Conference on Neural Networks, McAulay "Engineering Design Neural Networks Using Split Inversion Learning", vol. 4, Jun. 1987, pp. 635-642.
AIP Conference Proceedings 151: Neural Networks for Computing, Lapedes "Programming A Massively Parallel Computation Universal System: Static Behaviour", pp. 283-298, 1986.
Lampinen et al., Fast Self-Organization by the Probing Algorithm, Lappennranta University of Technology, Department of Information Technology, Box 20 Sf-53851 Lappeenranta, Finland, IJCNN, Jun. 1989, II-503-507.

Affiliated with

Also associated with

Rating

Learning method for a data processing system 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, 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 will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-766927