Locally Weighted Learning

  • Authors:
  • Christopher G. Atkeson;Andrew W. Moore;Stefan Schaal

  • Affiliations:
  • College of Computing, Georgia Institute of Technology, 801 Atlantic Drive, Atlanta, GA 30332-0280. E-mail: cga@cc.gatech.edu, sschaal@cc.gatech.edu;Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213. E-mail: awm@cs.cmu.edu;College of Computing, Georgia Institute of Technology, 801 Atlantic Drive, Atlanta, GA 30332-0280. E-mail: cga@cc.gatech.edu, sschaal@cc.gatech.edu

  • Venue:
  • Artificial Intelligence Review - Special issue on lazy learning
  • Year:
  • 1997

Quantified Score

Hi-index 0.08

Visualization

Abstract

This paper surveys locally weighted learning, a form of lazy learning andmemory-based learning, and focuses on locally weighted linear regression.The survey discusses distance functions, smoothing parameters, weightingfunctions, local model structures, regularization of the estimates and bias,assessing predictions, handling noisy data and outliers, improving thequality of predictions by tuning fit parameters, interference between oldand new data, implementing locally weighted learning efficiently, andapplications of locally weighted learning. A companion paper surveys howlocally weighted learning can be used in robot learning and control.