СКЛАДНІСТЬ БАЙЄСІВСЬКОЇ ПРОЦЕДУРИ ІНДУКТИВНОГО ВИВОДУ. ДИСКРЕТНИЙ ВИПАДОК
Behavior of inductive procedures depending on composition of learning sample is studied. It is shown that if in the learning sample there is no information about some class of objects or statistical information about a priori probabilities of classes then any procedure works badly and its error is s...
Saved in:
| Date: | 2006 |
|---|---|
| Main Authors: | , , , |
| Format: | Article |
| Language: | Ukrainian |
| Published: |
V.M. Glushkov Institute of Cybernetics of NAS of Ukraine
2006
|
| Online Access: | https://jais.net.ua/index.php/files/article/view/271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Journal Title: | Problems of Control and Informatics |
Institution
Problems of Control and Informatics| Summary: | Behavior of inductive procedures depending on composition of learning sample is studied. It is shown that if in the learning sample there is no information about some class of objects or statistical information about a priori probabilities of classes then any procedure works badly and its error is strictly positive. The lower bound of an error for the Bayes recognition procedure is obtained depending on a learning sample size and other parameters. It is proved that Bayesian procedure is suboptimal. |
|---|