Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery
Abstract
A combined neural network and rule-based approach is suggested as a general framework for pattern recognition. This approach enables unsupervised and supervised learning, respectively, while providing probability estimates for the output classes. The probability maps are utilized for higher level analysis such as a feedback for smoothing over the output label maps and the identification of unknown patterns (pattern "discovery"). The suggested approach is presented and demonstrated in the texture - analysis task. A correct classification rate in the 90 percentile is achieved for both unstructured and structured natural texture mosaics. The advantages of the probabilistic approach to pattern analysis are demonstrated.
Additional Information
© 1992 Morgan Kaufmann. This work is funded in part by DARPA under the grant AFOSR-90-0199 and in part by the Army Research Office under the contract DAAL03-89-K-0126. Part of this work was done at Jet Propulsion Laboratory. The advice and software support of the image-analysis group there, especially that of Dr. Charlie Anderson, is greatly appreciated.Attached Files
Published - 582-combined-neural-network-and-rule-based-framework-for-probabilistic-pattern-recognition-and-discovery.pdf
Files
Name | Size | Download all |
---|---|---|
md5:5ef9ce9d35577418ca8d66571e42fc58
|
1.7 MB | Preview Download |
Additional details
- Eprint ID
- 64018
- Resolver ID
- CaltechAUTHORS:20160127-130609305
- Defense Advanced Research Projects Agency (DARPA)
- DAAL03-89-K-0126
- Army Research Office (ARO)
- AFOSR-90-0199
- Air Force Office of Scientific Research (AFOSR)
- JPL
- Created
-
2016-01-27Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Series Name
- Advances in Neural Information Processing Systems
- Series Volume or Issue Number
- 4