Method for operating a neural network with missing and/or incomp

Details Method for operating a neural network with missing and/or incomp Method for operating a neural network with missing and/or incomp

1996-10-01

1998-10-06

MacDonald, Allen R.

395 23, 395 11, 395 24, G06F 1518

Patent

active

058190066

ABSTRACT:
A neural network system is provided that models the system in a system model (12) with the output thereof providing a predicted output. This predicted output is modified or controlled by an output control (14). Input data is processed in a data preprocess step (10) to reconcile the data for input to the system model (12). Additionally, the error resulted from the reconciliation is input to an uncertainty model to predict the uncertainty in the predicted output. This is input to a decision processor (20) which is utilized to control the output control (14). The output control (14) is controlled to either vary the predicted output or to inhibit the predicted output whenever the output of the uncertainty model (18) exceeds a predetermined decision threshold, input by a decision threshold block (22). Additionally, a validity model (16) is also provided which represents the reliability or validity of the output as a function of the number of data points in a given data region during training of the system model (12). This predicts the confidence in the predicted output which is also input to the decision processor (20). The decision processor (20) therefore bases its decision on the predicted confidence and the predicted uncertainty. Additionally, the uncertainty output by the data preprocess block (10) can be utilized to train the system model (12).

REFERENCES:
patent: 4802103 (1989-01-01), Fagging et al.
patent: 4872122 (1989-10-01), Alschuler et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5113483 (1992-05-01), Keeler et al.
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5335291 (1994-08-01), Kramer et al.
patent: 5402519 (1995-03-01), Inoue et al.
patent: 5467428 (1995-11-01), Ulug
patent: 5559690 (1996-09-01), Keeler et al.
"Layered Neural Networks with Gaussian Hidden Units as Universal Approximations" by Eric J. Hartman, James D. Keeler and Jacek M. Kowalski, Neural Computation 2, 1990, 210-215.
"Predicting the Future: Advantages of Semilocal Units" by Eric Hartman and James D. Keeler, Neural Computation 3, 1991, pp. 556-578.
"Interpolation and Extrapolation", Chapter 3 of Numerical Recipes: The Art of Scientific Computing by William H. Press, Brian P. Flannery, Saul A. Teukolsky and William T. Vettering, 1986, 77-101.
"Gross Error Detection and Data Reconciliation in Steam-Metering System" by R. W. Serth and W.A. Heenan, AIChE Journal, vol. 32, No. 5, May 1986, pp. 733-742.
"Thermal Power Prediction of Nuclear Power Plant Using NN and Parity Space Model", Myung-Sub Roh et al., IEEE Apr. 1991.
"On Correctiing Systematic Errors Without Analyzing Them by Performing a Repetitive Task", Antti Autere, IEEE 3-5, Nov. 1991.
"Stock Market Prediction System with Modular NN", T. Kimoto et al., IEEE 17-21, Jun. 1990.

Affiliated with

Also associated with

Rating

Method for operating a neural network with missing and/or incomp does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for operating a neural network with missing and/or incomp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for operating a neural network with missing and/or incomp will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-88276