Statistical Mechanics of Time Domain Ensemble Learning
Statistical Mechanics
2009-11-11 v1 Disordered Systems and Neural Networks
Abstract
Conventional ensemble learning combines students in the space domain. On the other hand, in this paper we combine students in the time domain and call it time domain ensemble learning. In this paper, we analyze the generalization performance of time domain ensemble learning in the framework of online learning using a statistical mechanical method. We treat a model in which both the teacher and the student are linear perceptrons with noises. Time domain ensemble learning is twice as effective as conventional space domain ensemble learning.
Keywords
Cite
@article{arxiv.cond-mat/0605176,
title = {Statistical Mechanics of Time Domain Ensemble Learning},
author = {Seiji Miyoshi and Tatsuya Uezu and Masato Okada},
journal= {arXiv preprint arXiv:cond-mat/0605176},
year = {2009}
}
Comments
10 pages, 10 figures