Statistical Mechanics of On-Line Mutual Learning with Many Linear Perceptrons
-
- Hara Kazuyuki
- Tokyo Metropolitan College of Industrial Technology
-
- Nakayama Yoichi
- Tokyo Metropolitan College of Technology
-
- Miyoshi Seiji
- Faculty of Engineering Science, Kansai University
-
- Okada Masato
- Graduate School of Frontier Sciences, The University of Tokyo Brain Science Institute, RIKEN
Search this article
Abstract
We propose a new mutual learning using many weak learners (or students) which converges into the identical state of Bagging that is kind of ensemble learning, within the framework of on-line learning, and have analyzed its asymptotic property through the statistical mechanics method. Mutual learning involving three or more students fundamentally differs from the two-student case with regard to the variety of selecting a student to act as teacher. The proposed model consists of two learning steps: many students independently learn from a teacher, and then the students learn from others through the mutual learning. In mutual learning, students learn from other students and the generalization error is improved even if the teacher has not taken part in the mutual learning. We demonstrate that the learning style of selecting a student to act as teacher randomly is superior to that of cyclic order by using principle component analysis.
Journal
-
- Journal of the Physical Society of Japan
-
Journal of the Physical Society of Japan 78 (11), 114001-114001, 2009
THE PHYSICAL SOCIETY OF JAPAN
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679173726976
-
- NII Article ID
- 130005437201
- 40016829621
- 210000108061
-
- NII Book ID
- AA00704814
-
- ISSN
- 13474073
- 00319015
-
- NDL BIB ID
- 10439021
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed