2016 Fiscal Year Final Research Report
Theory and Application of Information-Based Machine Learning
| Project/Area Number |
25700022
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (A)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | The University of Tokyo (2014-2016)
Tokyo Institute of Technology (2013) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Keywords | 機械学習 / 情報量 / 密度比 / 密度差 / 密度微分 / 教師付き学習 / 教師なし学習 / 強化学習 |
|---|
| Outline of Final Research Achievements |
In this research project, we developed methods for directly learning the density ratio and density difference without estimating each density, and based on them, we developed various machine learning algorithms. This includes algorithms of semi-supervised classification, unsupervised clustering, supervised causal inference, supervised dimension reduction, unsupervised dimension reduction, classification from positive and unlabeled data, supervised learning under target shift, and cross-domain object matching. We also developed methods for directly learning the density derivative without estimating the density itself, and based on them, we developed algorithms of modal regression and non-Gaussian component analysis.
|
| Free Research Field |
機械学習
|
