Optimization of training sets for neural-net processing of...

Data processing: artificial intelligence – Neural network – Learning method

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Reexamination Certificate

active

07072874

ABSTRACT:
An artificial neural network is disclosed that processes holography generated characteristic patterns of vibrating structures along with finite-element models. The present invention provides for a folding operation for conditioning training sets for optimally training forward-neural networks to process characteristic fringe patterns. The folding pattern increases the sensitivity of the feed-forward network for detecting changes in the characteristic pattern. The folding routine manipulates input pixels so as to be scaled according to the location in an intensity range rather than the position in the characteristic pattern.

REFERENCES:
patent: 5355528 (1994-10-01), Roska et al.
patent: 5371834 (1994-12-01), Tawel
patent: 5416616 (1995-05-01), Jenkins et al.
patent: 5428466 (1995-06-01), Rejman-Greene et al.
patent: 5465620 (1995-11-01), Sanderson et al.
patent: 5490062 (1996-02-01), Leach et al.
patent: 5631469 (1997-05-01), Carrieri et al.
patent: 5774376 (1998-06-01), Manning
patent: 5813406 (1998-09-01), Kramer et al.
patent: 6060710 (2000-05-01), Carrier et al.
patent: 6070098 (2000-05-01), Moore-Ede et al.
patent: 6268920 (2001-07-01), Ohlig
patent: 6574754 (2003-06-01), Smith
patent: 6941026 (2005-09-01), Nadabar et al.
patent: 06-180602 (1994-06-01), None
Arthur J. Decker, “Training Data Optimized and Conditioned to learn Characteristic Patterns of Vibrating Blinks and Fan Blades”, 2000.
Arthur J. Decker, “Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography” 90th Symposium Cosponsored by The Advisory Group for Aerospace Research and Development and the Propulsion and Energetic Panel, Oct. 1997.
Arthur J. Decker, “Model-Trained Neural Network and Electronic Holography Demonstrated to Detect Damage in Blades”, NASA, 1997.
Kutanov et al, “Holographic-Disk-Based Optical Neural Network”, Optics Letters, vol. 7, No. 13, Jul. 1, 1997.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Optimization of training sets for neural-net processing of... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Optimization of training sets for neural-net processing of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimization of training sets for neural-net processing of... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3552246

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.