Computer Science – Learning
Scientific paper
2006-12-22
Computer Science
Learning
12 pages, 5 pages
Scientific paper
10.1143/JPSJ.76.044003
In the framework of on-line learning, a learning machine might move around a teacher due to the differences in structures or output functions between the teacher and the learning machine. In this paper we analyze the generalization performance of a new student supervised by a moving machine. A model composed of a fixed true teacher, a moving teacher, and a student is treated theoretically using statistical mechanics, where the true teacher is a nonmonotonic perceptron and the others are simple perceptrons. Calculating the generalization errors numerically, we show that the generalization errors of a student can temporarily become smaller than that of a moving teacher, even if the student only uses examples from the moving teacher. However, the generalization error of the student eventually becomes the same value with that of the moving teacher. This behavior is qualitatively different from that of a linear model.
Miyoshi Seiji
Okada Masato
Urakami Masahiro
No associations
LandOfFree
Statistical Mechanics of On-line Learning when a Moving Teacher Goes around an Unlearnable True Teacher 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 On-line Learning when a Moving Teacher Goes around an Unlearnable True Teacher, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical Mechanics of On-line Learning when a Moving Teacher Goes around an Unlearnable True Teacher will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-531040