2010 Fiscal Year Final Research Report
Learning non-linear concepts based on random projection
| Project/Area Number |
20500001
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Fundamental theory of informatics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
TAKIMOTO Eiji Kyushu University, 大学院・システム情報科学研究院, 教授 (50236395)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Keywords | 計算学習理論 / ブースティング / マージン最大化 / ランキング学習 / オンライン予測 / エネルギー複雑度 / 論理式複雑さ |
|---|
| Research Abstract |
We investigate new schema for learning non-linear concepts by combining random projection with linear classifiers. In particular, we show that a boosting algorithm naturally results in our learning scheme, where the algorithm randomly chooses appropriate rules in a given rule class and produces as a final hypothesis a linear combination of them. On the other hand, we give lower bounds on the complexity of constant depth threshold circuits, which serve the most natural hypothesis class for our learning schema. The bounds imply theoretical limitations for our shema.
|
