 
|
|
|
|
|
|
|
|
|
SMD127 Learning with Bayesian Network 7.5 ECTS credits | |
|
TIMEPERIOD: Quarter III LANGUAGE:English EXAMINER Ramin Yasdi Univ lekt PREREQUISITES B-level, knowledge in Machine Learning is useful. COURSE AIM To present foundations of methods and algorithms in the area of Bayesian Learning CONTENTS A Bayesian network is a graphical model that encodes relationships among variables of interest. When used in conjunction with statistical techniques, the graphical model has several advantages for data analysis. One, because the model encodes dependencies among all variables, it readily handles situations where some data entries are missing. Two, a Bayesian network can be used to learn causal relationships, and hence can be used to gain understanding about a problem domain and to predict the consequences of intervention. Three, because the model has both a causal and probabilistic semantics, it is an ideal representation for combining prior knowledge (which often comes in causal form) and data. Four, Bayesian statistical method in conjunction with Bayesian networks offer an efficient and principled approach for avoiding the over fitting of data.
Over the last decade, the Bayesian network has become a popular representation for encoding uncertain expert knowledge in Expert Systems. More recently, reserarchers have developed methods for leraning Bayesian networks from data. The techniques that have been developed are new and still evolving, but they have been shown to be remarkably effective for some data analysis problems.
In this course, we provide an introduction to Bayesian networks and associated Bayesian techniques for extracting and encoding knowledge from data. We discuss methods for constructing Bayesian networks from prior knowledge and summarize Bayesian statistical methods for using data to improve this models. With regards to latter task, we describe methods for learning both parameters and structure of Bayesian networks, including techniques for learning with incomplete data. In addition, we relate Bayesian network methods for leraning to techniques for supervised and unsupervised learning. We illustrate hte graphical modeling approach using a real world case study.
| |
| Project work | 7.50ECTS |
|
COURSE LITERATURE An Introduction to Bayesian Networks, Finn V.Jensen, UCL Press, 96 Further information: International Office Course information from the department: http://www.sm.luth.se/~yasdi |
Web Editor: Karin.Lindholm@dc.luth.se
| The University | Student | Research | Search | Contact us | In Swedish |
 LULEÅ UNIVERSITY OF TECHNOLOGY University Campus, Porsön, 971 87 Luleå. Tel. +46 (0) 920-91 000, fax +46 (0) 920-91 399 |