Project/Area Number |
02452155
|
Research Category |
Grant-in-Aid for General Scientific Research (B)
|
Allocation Type | Single-year Grants |
Research Field |
情報工学
|
Research Institution | Tokyo Institute of Technology |
Principal Investigator |
OGAWA Hidemitsu Tokyo Institute of Technology, Faculty of Engineering Professor, 工学部, 教授 (50016630)
|
Co-Investigator(Kenkyū-buntansha) |
YAMASHITA Yukihiko Tokyo Institute of Technology, Faculty of Engineering Associate, 工学部, 助手 (90220350)
KUMAZAWA Itsuo Tokyo Institute of Technology, Faculty of Engineering Associate Professor, 工学部, 助教授 (70186469)
|
Project Period (FY) |
1990 – 1991
|
Project Status |
Completed (Fiscal Year 1991)
|
Budget Amount *help |
¥5,700,000 (Direct Cost: ¥5,700,000)
Fiscal Year 1991: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 1990: ¥4,500,000 (Direct Cost: ¥4,500,000)
|
Keywords | Image restoration / Neural network / Learning / Generalization / Filtering / Nonlinear processing / Statics / Over-learning / フイルタ |
Research Abstract |
A theory for neural network learning which is very effective for analyzing the generalization ability and the overlearning problem is developed. This theory is based on the image restoration theories proposed by the head investigator of this project. Although the problems of generalization and image restoration seem to have nothing in common, we have shown that both problems can be dealt with under the same methodology if we formalize them as a kind of inverse problem. This novel approach provides an analytical and quantitative method for the problems of generalization and over-learning which have been so far treated qualitatively. Followings are the major results obtained in this project. ・A new framework of generalization which can extract general structures among training samples is developed based on the image restoration theories. ・We analyze the generalization ability of the back-propagation using the framework. ・We provide a way of choosing, training samples which does not cause the over-learning problem and gives an optimal generalizing ability. ・Above theoretical results are examined by some computer simulations.
|