Develop of a new growing neural network where the learning algorithm is established from the generative model
| Project/Area Number |
23700270
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Fuzzy Logic Systems Institute |
|---|
Principal Investigator |
TOKUNAGA Kazuhiro 一般財団法人ファジィシステム研究所, 研究部, 主任研究員 (00432956)
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2012: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2011: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 成長型ニューラルネットワーク / 自己組織化マップ / ニューラルネットワーク / 自己組織化 / Growing Neural Gas |
|---|
| Research Abstract |
In this study, a learning algorithm of a growing neural network was established theoretically from the view point of a generating model. Thus, the proposal method has robustness to following problems comparing with conventional growing neural networks;weakness for noise, generation of redundancy nodes, requirement of a lot of input data and so on.
|
Report
(3 results)
Research Products
(8 results)
