Method for editing an input quantity for a neural network

Details Method for editing an input quantity for a neural network Method for editing an input quantity for a neural network

1996-08-19

1998-01-06

Hafiz, Tariq R.

395 23, G06E 100, G06E 300, G06F 1518

Patent

active

057064016

ABSTRACT:
In a method for supplementing missing data in a time series used as an input to a neural network or for improving noise-infested data supplied to a neural network, error distribution densities for the missing values are calculated on the basis of the known measured values from the time series and their known or predetermined error distribution density, and samples are taken from this error distribution density according to the Monte Carlo method. These each lead to an estimated or predicted value whose average is introduced for the value to be predicted. The method can be employed for the operation as well as for the training of the neural network, and is suitable for use in all known fields of utilization of neural networks.

REFERENCES:
patent: 5479576 (1995-12-01), Watanabe et al.
"Bayesian Back-Propagation," Buntine et al, Complex Systems, vol. 5, (1991), pp. 605-643.
"Supervised Learning From Incomplete Data Via An Em Approach," Ghahramani et al, from Advances In Neural Information Processing Sysems, vol. 6, Cowan et al, Eds. (1994) pp. 120-127.
"Training Neural Networks With deficient Data," Tresp et al, Advances In Neural Information Systems, vol. 6, Cowan, Eds. (1994) pp. 128-135.
Marko et al. "Neural Network Application to Comprehensive Engine Diagnostics" Systems, Man, and Cybernetics, 1992 Int'l Conf., pp. 1016-1022, Aug. 1992.

Affiliated with

Also associated with

Rating

Method for editing an input quantity for a neural network 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 editing an input quantity for a neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for editing an input quantity for a neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2336756