| Project/Area Number |
24500283
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Tokai University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAKEUCHI Haruhiko 独立行政法人, 産業技術総合研究所, 主任研究員 (00357401)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | ニューラルネットワーク / 自己組織化マップ / 情報論的方法 / 能動学習 / 多層ニューラルネットワーク / 相互情報量 / 競合学習 / 深層学習 / 内部表現 / 段階的情報最大 / 変数選択 / 機械学習 / 情報理論 / 教師付学習 / 自由エネルギー / 重要性分析 / クラス構造 |
|---|
| Outline of Final Research Achievements |
The models in neural networks have aimed to create representations faithful to input patterns as much as possible. However, it has turned out that the faithful representations are not necessarily effective in actual situations. Thus, the present study attempted to create multiple representations, depending on different situations. However, in the course of this pursuit to the open representations, it has turned out that it is necessary to build up more powerful network models for realizing open representations. For this, new multi-layered neural networks model was developed based on the information-theoretic self-organizing maps. In addition, the definition of information content should be changed to take into account the possibility of the information more exactly. Finally, the information theoretic methods should be simplified to be applicable to large data sets.
|
