The Sample Complexity of Learning Fixed-Structure Bayesian Networks |
| |
Authors: | Dasgupta Sanjoy |
| |
Affiliation: | (1) Department of Computer Science, University of California, Berkeley, CA, 94720 |
| |
Abstract: | We consider the problem of PAC learning probabilistic networks in the case where the structure of the net is specified beforehand. We allow the conditional probabilities to be represented in any manner (as tables or specialized functions) and obtain sample complexity bounds for learning nets with and without hidden nodes. |
| |
Keywords: | Bayesian networks PAC learning sample complexity |
本文献已被 SpringerLink 等数据库收录! |