| Project/Area Number |
09450171
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
計測・制御工学
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
HIRASAWA Kotaro Information Science and Electrical Engineering, Kyushu University, Professor, 大学院・システム情報科学研究科, 教授 (70253474)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
OHBAYASI Masanao Engineering, Kyushu University, Assistant Professor, 工学部, 助教授 (60213849)
MURATA Junichi Information Science and Electrical Engineering, Kyushu University, Assistant Professor, 大学院・システム情報科学研究科, 助教授 (60190914)
胡 敬炉 九州大学, 大学院システム情報科学研究科, 助手 (50294905)
|
|---|
| Project Period (FY) |
1997 – 1999
|
| Project Status |
Completed (Fiscal Year 1999)
|
| Budget Amount *help |
¥9,500,000 (Direct Cost: ¥9,500,000)
Fiscal Year 1999: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 1998: ¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 1997: ¥6,200,000 (Direct Cost: ¥6,200,000)
|
|---|
| Keywords | Neural Networks / Genetic Algorithm / Fuzzy / Universal Learning Networks / Higher Order Derivatives / Symbiosis / Robust Control / Chaos Control / モデル化 / 学習 / 確率 / 制御 / 安定性 / カオス / 集中化・多様化 / ネットワーク / 離散事象 / オートマトン / ゲート |
|---|
| Research Abstract |
Since the first proposal of a neuron model by Mc Culloch and Pitts in the 1940's, especially after the revitalization of artificial neural networks in 1980's, a variety of neural networks have been devised and are now applied in many fields. The vast majority of neural networks in use are those networks whose parameters or weights are tuned by gradiant-based supervised learning. This category includes feedfoward networks or multilayer parceptrons, various types of recurrent neural networks, radial basis function networks, fuzzy neural networks, and some networks with special architectures, such as time delay neural networks. These networks seemingly have different architectures and are trained by distinguishable training algorithms. In essence, however, they can be unified in a single framework in regard to both their architectures and learning algorithms. Universal Learning Networks (ULN's) have been proposed, as the name indicates, to provide a universal framework for the class of neural networks and moreover to model and control complex systems because most of the general complex systems in the real world can be modeled by the networks whose nodes represent the processing elements, and the branch between the nodes can describe the relation among the processes. Unification of a variety of network architectures which can describe the complex systems and unification of their learning algorithms are an objective of ULN's. This provides a consistent viewpoint for the various kinds of networks.
|
