A case study of bayesian network theory refinement for preference elicitation | |
| Author | Rachanee Srisurangkul |
| Call Number | AIT Thesis no.IM-03-01 |
| Subject(s) | Bayesian statistical decision theory Decision support systems Neural networks (Computer science) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. IM-03-01 |
| Abstract | This thesis explores the use of one particular theory refinement technique, Bayesian networks (BN), to learn user preferences. Bayesian networks are in efficient and effective representation of probability distributions via conditional independence. We demonstrate this approa,ch through the example, which involves preference unqer certainty. The initial network is derived directly from a domain theory of propositional Hom-clause rules that encode assumptions concerning preferential independence. The network structure and parameters are then refined by training on data representing an individual's preferences. We empirically compare the Bayesian network with a neural network approach in terms of learning rate and accuracy. |
| Year | 2003 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. IM-03-01 |
| Type | Thesis |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Haddawy, Peter; |
| Examination Committee(s) | Phan Minh Dung;Dentcho N Batanov; |
| Scholarship Donor(s) | Telephone Organization of Thailand; |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 2003 |