On-line learning methods for Gaussian processes

被引：0

作者：

Oba, S ^{[1
]}

Sato, M

Ishii, S

机构：

[1] Nara Inst Sci & Technol, Ikoma 6300101, Japan

[2] ATR Int, Kyoto 6190288, Japan

来源：

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2003年 / E86D卷 / 03期

关键词：

Gaussian process; on-line learning; Bayesian estimation;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We propose two modifications of Gaussian processes, which aim to deal with dynamic environments. One is a weight decay method that gradually forgets old data, and the other is a time stamp method that regards the time course of data as a Gaussian process. We show experimental results when these modifications are applied to regression problems in dynamic environments. The weight decay method is found to follow the environmental change by automatically ignoring the past data, and the time stamp method is found to predict linear alteration.

引用

页码：650 / 654

页数：5