Method for using a feed forward neural network to perform classi

Details Method for using a feed forward neural network to perform classi Method for using a feed forward neural network to perform classi

1991-12-02

1994-10-25

Downs, Robert W.

Image analysis

Histogram processing

For setting a threshold

395 23, 382 14, G06F 1518

Patent

active

053596994

ABSTRACT:
An artificial neural network detects points in feature space outside of a boundary determined by a set of sample data. The network is trained using pseudo data which compensates for the lack of original data representing "abnormal" or novel combinations of features. The training process is done iteratively using a net bias parameter to close the boundary around the sample data. When the neural net stabilizes, the training process is complete. Pseudo data is chosen using several disclosed methods.

REFERENCES:
Lippmann, R. P. "An Introduction to Computing with Neural Nets," IEEE ASSP Magazine, Apr. 1987, 4-22.
Goryn et al., "Conjugate Gradient Learning Algorithms for Multilayer Perceptions," Proc. 32nd Midwest Symp. on Circuits and Systems, Aug. 1989, 736-739.
Lippman, R. P., "Pattern Classification Using Neural Networks," IEEE Comm. Magazine, Nov. 1989, 47-64.
Ahmad et al., "Scaling and Generalization in Neural Networks: A Case Study," Advances in Neural Info. Proc. Syst. I, 1989, 160-168.
Hanson et al., "Comparing Biases for Minimal Network Construction with Back-Propagation," Advances in Neural Info. Proc. Syst. I, 1989, 177-185.
Caudill, M., "Using Neural Nets: Diagnostic Expert Nets," AI Expert, Sep. 1990, 43-47.
Guo et al., "Sensor Failure Detection and Recovery by Neural Networks," Intl. Joint Conf. on Neural Networks, Jul. 1991, I-221-I-226.
Zhu et al., "ECG Monitoring with Artificial Neural Networks," 2nd Intl. Conf. on Artificial Neural Networks, Nov. 1991, 205-209.
Jang et al., "Application of Neural Networks for Seismic Phase Identification," 1990 IEEE Intl. Joint Conf. on Neural Networks, Nov. 1991, 899-904.
Sakaue et al., "Reduction of Necessary Precision for the Learning of Pattern Recognition," 1991 IEEE Intl. Joint Conf. on Neural Networks, Nov. 1991, 1795-1800.
Lawrence, J., "Data Preparation for a Neural Network," AI Expert, Nov. 1991, 34-41.
"An Artificial Neural Network to Solve Multidimensional Boundary Determination Problems", A Thesis Submitted to Graduate Faculty of Rensselaer Polytechnic Institute, Rensselaer, N.Y. by Paul A. Delano, pp. 1-69-Dec. 1990.
"Neural Nets for Fault Detection", Submitted to The 2nd Government Neural Network Applications Workshop, Huntsville, Ala. by David W. Tong-pp. 1-4 Sep. 1991.
"Neural Nets for Abnormality Detection" by David W. Tong & Paul A. Delano, General Electric Corporate Research & Development, Schenectady, N.Y.-pp. 1-9, 1991.

Affiliated with

Also associated with

Rating

Method for using a feed forward neural network to perform classi 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 using a feed forward neural network to perform classi, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for using a feed forward neural network to perform classi will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-142015