Neural network system with sampling data

Details Neural network system with sampling data Neural network system with sampling data

1994-10-03

1996-12-31

Davis, George B.

395 21, 395 22, 395 24, G06F 1518

Patent

active

055902430

ABSTRACT:
A neural network system includes input, intermediate and output layers, each layer containing at least one neural network element, each having an input and output, for simulating a neuron; and a plurality of inter-layer connections between neural elements wherein each input layer element has a connection to at least one intermediate layer element, and each intermediate layer element has a connection to at least one output layer element. Each inter-layer connection has a connecting weight. The system further includes sampling data and teaming data. The sampling data has pairs of values, each pair including an input value and corresponding output value, the input value having regular intervals. The learning data has at least three pairs of values, each pair including an input value and corresponding desired output value, the input values having irregular intervals. The intermediate layer elements are assigned unique sampling data value pairs and have unique sampling functions derived by translating original sampling functions by sampling data input values assigned to the neural elements. The sampling function defines a relationship between the input and output of the neural element. The connecting weight for each connection between an intermediate layer element and an output layer element is set to the sampling data output value assigned to the intermediate layer element. The system further includes a training mechanism that adjusts the connecting weights to minimize errors between learning data output values and actual output values obtained by applying the learning data input values to the neural network.

REFERENCES:
patent: 4874963 (1989-10-01), Alspector
patent: 4912654 (1990-03-01), Wood
patent: 5046020 (1991-09-01), Filkin
patent: 5052043 (1991-09-01), Goborski
patent: 5056037 (1991-10-01), Eberhardt
patent: 5107454 (1992-04-01), Niki
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5142666 (1992-08-01), Yoshizawa et al.
patent: 5148045 (1992-09-01), Oyanagi
patent: 5168550 (1992-12-01), Sakaue et al.
patent: 5175796 (1992-12-01), Refregier et al.
Specht Probabality Neural Network for Classification, Mapping, or Associative Memory, IEEE Int. Conf. on Neural Networks, Jul. 1988.
Wasserman et al, "Neural Network, part 2" IEEE Expert, 1988.
Littleston et al, "Learning in Layered Network with Many Fixed-function Hidden Nodes" IEEE Ist Int. Conf. on Neural Networks, Jun. 1987.
Richard O. Duda, Peter E. Hart, "Pattern Classification and Scene Analysis", 1973, pp. 88-99, 172-175, Wiley-Interscience Publication.
Learning Representations by Back-Propagating Errors, Rumelhart, et al., pp. 533-536, Nature vol. 323, Oct. 9, 1986.
A Neural Model of Interpolation or Interpolation with Blobs, Shustorovich, pp. 529-532, Eastman Kodak Company.
Theory of the Back-Propagation Neural Network, Hecht-Nielson, pp. 593-605, HNC, Inc., Univ. of California at San Diego.

Affiliated with

Also associated with

Rating

Neural network system with sampling data 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 system with sampling data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network system with sampling data will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1148308