Neural network learning system inferring an input-output relatio

Details Neural network learning system inferring an input-output relatio Neural network learning system inferring an input-output relatio

1995-02-23

1995-12-26

MacDonald, Allen R.

Boots, shoes, and leggings

395 21, 364130, G06F 1518

Patent

active

054795761

ABSTRACT:
A neural network learning system in which an input-output relationship is inferred. The system includes a probability density part for determining a probability density on a sum space of an input space and an output space from a set of given input and output samples by learning, the probability density on the sum space being defined to have a parameter, and an inference part for inferring a probability density function based on the probability density from the probability density part, so that an input-output relationship of the samples is inferred from the probability density function having a parameter value determined by learning, the learning of the parameter being repeated until the value of a predefined parameter differential function using a prescribed maximum likelihood method is smaller than a prescribed reference value.

REFERENCES:
patent: 4885757 (1989-12-01), Prorence
patent: 4937872 (1990-06-01), Hopfield et al.
patent: 4945494 (1990-07-01), Penz et al.
A Non Competitive Model for Unsupervised Learning T. Hrycej IEEE/16-18 Oct. 1989.
Maximum Likelihood Density Estimation by means of PDF Network Jian-xiong Wu et al. IEEE/Sep. 1990.
An Application of Neural Net Technology to Surveillance Information Correlation and Battle Outcome Prediction P. Suzie Maloney, PhD, IEEE/22-26 May 1989.
A Learning Algorithm for Boltzman Machines D. H. Ackley Dec. 31, 1985.
C. H. Anderson et al., "A Bayesian Probability Network", American Institute of Physics Proceedings, Snowbird, Utah, 1986, pp. 6-11.
P. Susie Maloney et al., "The Use of Probabilistic Neural Networks to Improve Solution Times for Hull-to-Emitter Correlation Problems", IJCNN International Joint Conference on Neural Networks, Sheraton Washington Hotel, Washington, D.C., Jun. 1989, pp. I-289 through I-294.
Gerhard Paass, "Structured Probabilistic Neural Networks", Neuro-Nimes '89 International Workshop Neural Networks & Their Applications, Nimes, France, Nov. 1989, pp. 345-359.
Nasser M. Nasrabadi et al., "Vector Quantization of Images Based Upon the Kohonen Self-Organizing Feature Maps", IEEE International Conference on Neural Networks, San Diego, California, Jul. 1988, pp. I-101 through I-108.
Donald F. Specht, "Probabilistic Neural Networks for Classification, Mapping, or Associative Memory", IEEE International Conference on Neural Networks, San Diego, California, Jul. 1988, pp. I-525 through I-532.
"A General Regression Neural Network", by Donald F. Specht from IEEE transactions on neural networks, vol. 2, No. 6, Nov. 1991.

Affiliated with

Also associated with

Rating

Neural network learning system inferring an input-output relatio 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 learning system inferring an input-output relatio, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network learning system inferring an input-output relatio will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1375738