Neural network with semi-localized non-linear mapping of the inp

Details Neural network with semi-localized non-linear mapping of the inp Neural network with semi-localized non-linear mapping of the inp

1990-06-15

1992-05-12

MacDonald, Allen R.

395 24, G06F 1518

Patent

active

051134837

ABSTRACT:
A neural network includes an input layer comprising a plurality of input units (24) interconnected to a hidden layer with a plurality of hidden units (26) disposed therein through an interconnection matrix (28). Each of the hidden units (26) is a single output that is connected to output units (32) in an output layer through an interconnection matrix (30). Each of the interconnections between one of the hidden units (26) to one of the output units (32) has a weight associated therewith. Each of the hidden units (26) has an activation in the i'th dimension and extending across all the other dimensions in a non-localized manner in accordance with the following equation: ##EQU1## that the network learns by the Back Propagation method to vary the output weights and the parameters of the activation function .mu..sub.hi and .sigma..sub.hi.

REFERENCES:
Marr, "A Theory of Cerebellar Cortex," Journal of Physiology, 202, 1969 pp. 437-470.
Albus, "Brains, Behavior & Robotics," Byte Books, Peterborough, N.H., Chapter 6, A Neuological Model, 1981, pp. 139-179.
Ito, "The Cerebellum and Neural Control," Raven Press, Chapter 10, Neuronal Network Model, 1984, pp. 115-130.
Farmer et al. "Predicting Chaotic Time Series," Physical Letters Review, 59, 1987, pp. 845-848.
Farmer et al. "Exploiting Chaos to Predict the Future and Reduce Noise", Los Alamos Preprint 88-901, 1988, pp. 1-54.
Keeler, "Comparison of Kanerva's SDM to Hopfield-Type Neural Networks," Cognitive Science, 12 1988, pp. 299-329.
Rogers, "Statistical Prediction with Kanerva's Sparse Distributed Memory," Neural Information Processing Systems, Edited by D. Touretzky, Morgan Kaufmann Publishers, San Mateo, CA, 1989, pp. 586-593.
Lapedes et al., "Nonlinear Signal Processing Using Neural Networks: Prediction and System Modelling," Los Alamos Technical Report LA-UR-87-2662, 1987.
Moody et al., "Learning with Localized Receptive Fields," Proceedings of the 1988 Connectionist Models Summer School, edited by D. Touretsky, G. Hinton, T. Sejnowski, and M. Kaufmann, 1988, pp. 133-143.

Affiliated with

Also associated with

Rating

Neural network with semi-localized non-linear mapping of the inp 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 with semi-localized non-linear mapping of the inp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network with semi-localized non-linear mapping of the inp will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2427706