Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2006-09-22
Physics
Condensed Matter
Disordered Systems and Neural Networks
11 pages, 7 figures
Scientific paper
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.
Miyoshi Seiji
Okada Masato
No associations
LandOfFree
Statistical Mechanics of Linear and Nonlinear Time-Domain Ensemble Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Statistical Mechanics of Linear and Nonlinear Time-Domain Ensemble Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical Mechanics of Linear and Nonlinear Time-Domain Ensemble Learning will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-129613