1996 Fiscal Year Final Research Report Summary
Machine Discovery by Learning Algorithms
| Project/Area Number |
06452405
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | KYUSHU UNIVERSITY |
|---|
Principal Investigator |
ARIKAWA Setsuo Graduate School of Information Science and Electrical Engineering, Department of Informatics, KYUSHU UNIVERSITY Professor, 大学院・システム情報科学研究科, 教授 (40037221)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MIYANO Satoru University of Tokyo, Medical Science Institute, Professor, 医科学研究所, 教授 (50128104)
EIJU Hirowatari Graduate School of Information Science and Electrical Engineering, Department of, 大学院・システム情報科学研究科, 助手 (60274429)
SHINOHARA Ayumi Graduate School of Information Science and Electrical Engineering, Department of, 大学院・システム情報科学研究科, 助教授 (00226151)
ZEUGMANN Thomas Graduate School of Information Science and Electrical Engineering, Department of, 大学院・システム情報科学研究科, 助教授 (60264016)
NIIJIMA Kouichi Graduate School of Information Science and Electrical Engineering, Department of, 大学院・システム情報科学研究科, 教授 (30047881)
|
|---|
| Project Period (FY) |
1994 – 1996
|
| Keywords | machine learning / machine discovery / computational learning theory / inductive inference / PAC learning / learning from numerical data / knowledge discovery in database / logic of machine discovery |
|---|
| Research Abstract |
This project aimed at developing machine discovery systems based upon firm theoretical foundations of machine learning algorithms. In this project we have focused our attention specially on (1) computational logic of machine discovery, (2) knowledge representation for machine discovery, (3) machine discovery by PAC learning, (4) machine discovery in databases, and (5) making machine discovery algorithms parallel.
First we have developed a logic of machine discovery compared with the logic of scientific discovery by K.Popper. We have made it clear that the essential of machine discovery is to be able to refute the hypothesis space itself by some observed facts, and showed that there are such rich hypothesis spaces in the framework of the elementary formal systems. Since scientific data are mostly numerical, we have studied representation of real numbers and real-valued functions in terms of recursive reals and interval analysis, and developed a method of identifying differential equations.
We have extended our results on the logic of machine discovery to the PAC learning, which can cope with probably approximately correct hypotheses.
Concerning the machine discovery in database, we have developed a machine discovery system based upon a decision trees over regular patterns called BONSAI,made it parallel, and also developed a prediction system for some domains in amino acid sequences. We have also made some experiments on the field of molecular biology, and got very successful results.
|
Research Products
(17 results)
