Statistical Mechanics of Linear and Nonlinear Time-Domain Ensemble Learning
-
- Miyoshi Seiji
- Department of Electronic Engineering, Kobe City College of Technology
-
- Okada Masato
- Division of Transdisciplinary Sciences, Graduate School of Frontier Sciences, The University of Tokyo RIKEN Brain Science Institute
Search this article
Abstract
Conventional ensemble learning combines students in the space domain. In this paper, however, we combine students in the time domain and call it time-domain ensemble learning. We analyze, compare, and discuss the generalization performances regarding time-domain ensemble learning of both a linear model and a nonlinear model. Analyzing in the framework of online learning using a statistical mechanical method, we show the qualitatively different behaviors between the two models. In a linear model, the dynamical behaviors of the generalization error are monotonic. We analytically show that time-domain ensemble learning is twice as effective as conventional ensemble learning. Furthermore, the generalization error of a nonlinear model features nonmonotonic dynamical behaviors when the learning rate is small. We numerically show that the generalization performance can be improved remarkably by using this phenomenon and the divergence of students in the time domain.
Journal
-
- Journal of the Physical Society of Japan
-
Journal of the Physical Society of Japan 75 (12), 124002-, 2006
THE PHYSICAL SOCIETY OF JAPAN
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679166895744
-
- NII Article ID
- 110005716678
- 210000106444
-
- NII Book ID
- AA00704814
-
- BIBCODE
- 2006JPSJ...75l4002M
-
- ISSN
- 13474073
- 00319015
-
- NDL BIB ID
- 8572901
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed