Learning with a probabilistic teacher
- 1 July 1970
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 16 (4) , 373-379
- https://doi.org/10.1109/tit.1970.1054472
Abstract
The Bayesian learning scheme is computationally infeasible for most of the unsupervised learning problems. This paper suggests a learning scheme, "learning with a probabilistic teacher," which works with unclassified samples and is computationally feasible for many practical problems. In this scheme a sample is probabilistically assigned with a class with appropriate probabilities computed using all the information available: Then the sample is used in learning the parameter values given this assignment of the class. The convergence of the scheme is established and a comparison with the best linear estimator is presented.Keywords
This publication has 5 references indexed in Scilit:
- Optimal recursive estimation with uncertain observationIEEE Transactions on Information Theory, 1969
- On pattern classification algorithms introduction and surveyProceedings of the IEEE, 1968
- LEARNING TO RECOGNIZE PATTERNS WITHOUT A TEACHERPublished by Defense Technical Information Center (DTIC) ,1965
- REPRODUCING DISTRIBUTIONS FOR MACHINE LEARNINGPublished by Defense Technical Information Center (DTIC) ,1963
- Learning to recognize patterns in a random environmentIEEE Transactions on Information Theory, 1962