A STUDY OF RESOLVING LONG TAIL PHENOMENA BY MACHINE LEARNING
Project/Area Number |
21240011
|
Research Category |
Grant-in-Aid for Scientific Research (A)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | The University of Tokyo |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
YOSHIDA Minoru 東京大学, 情報基盤センター, 助教 (40361688)
KIYOTA Youji 東京大学, 情報基盤センター, 助教 (10401316)
SATO Issei 東京大学, 情報基盤センター, 助教 (90610155)
|
Co-Investigator(Renkei-kenkyūsha) |
NINOMIYA Takashi 東京大学, 情報基盤センター, 講師 (20444094)
|
Project Period (FY) |
2009 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥47,060,000 (Direct Cost: ¥36,200,000、Indirect Cost: ¥10,860,000)
Fiscal Year 2011: ¥14,560,000 (Direct Cost: ¥11,200,000、Indirect Cost: ¥3,360,000)
Fiscal Year 2010: ¥14,950,000 (Direct Cost: ¥11,500,000、Indirect Cost: ¥3,450,000)
Fiscal Year 2009: ¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
|
Keywords | 知識発見 / データマイニング / 機械学習 / テキストマイニング / Web / ネットワークデータ / 統計 / 曖昧正解消 / プライバシー保護 / 言語学習 / クラスタリング / 曖昧性解消 / テキスト / 非負行列分解 / GPU / アルゴリズム |
Research Abstract |
We developed a clustering system which makes clusters of web pages in response to a person name query in 2009 as planned, and evaluate it experimentally. In 2010, our contribution is a new non-negative probabilistic matrix decomposition algorithm and application of Variational Bayes method to Pitman-YO process. In 2011, our contribution for PPDM is a link analysis algorithm with public key encryption and specific protocol. In 2012, we developed a new online learning algorithm as well as new PPDM method.
|
Report
(4 results)
Research Products
(57 results)