Uncertainty inference by probabilistic models
| Project/Area Number |
20300053
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
SATO Taisuke Tokyo Institute of Technology, 大学院・情報理工学研究科, 教授 (90272690)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KAMEYA Yoshitaka 東京工業大学, 大学院・情報理工学研究科, 助教 (60361789)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥13,130,000 (Direct Cost: ¥10,100,000、Indirect Cost: ¥3,030,000)
Fiscal Year 2010: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2009: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2008: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
|
|---|
| Keywords | 学習と知識獲得 / shared BDD / order-encoding / PRISM / Viterbi推論 / BDD / 確率計算 / BDD-EMアルゴリズム / 変分ベイズ / 一般化内側・外側確率アルゴリズム |
|---|
| Research Abstract |
Currently techniques from machine learning and statistical natural language processing are popular in various fields including data-mining and bioinformatics. However they are feature-based and it is difficult to capture interdependent relationships in real data. We have developed a logic-based modeling language PRISM which unifies logical semantics and statistical parameter learning. It separates model description by logical formulas from their probability computation and parameter learning, thereby enabling an expressive yet efficient complex probabilistic modeling.
|
Report
(4 results)
Research Products
(35 results)
