Electronic Resource
Springer
Machine learning
29 (1997), S. 165-180
ISSN:
0885-6125
Keywords:
Bayesian networks
;
PAC learning
;
sample complexity
Source:
Springer Online Journal Archives 1860-2000
Topics:
Computer Science
Notes:
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.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1023/A:1007417612269
Permalink
|
Location |
Call Number |
Expected |
Availability |