Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Instance-Based Learning

  • Eamonn Keogh
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_409



Instance-based learning refers to a family of techniques for classification  and regression, which produce a class label/predication based on the similarity of the query to its nearest neighbor(s) in the training set. In explicit contrast to other methods such as decision trees and neural networks, instance-based learning algorithms do not create an abstraction from specific instances. Rather, they simply store all the data, and at query time derive an answer from an examination of the query’s nearest neighbor(s).

Somewhat more generally, instance-based learning can refer to a class of procedures for solving new problems based on the solutions of similar past problems.

Motivation and Background

Most instance-based learning algorithms can be specified by determining the following four items:
  1. 1.

    Distance measure: Since the notion of similarity is being used to...

This is a preview of subscription content, log in to check access.

Recommended Reading

  1. Aha, D. W., Kibler, D., & Albert, M. K. (1991). Instance-based learning algorithms. Machine Learning, 6, 37–66.Google Scholar
  2. Ding, H., Trajcevski, G., Scheuermann, P., Wang, X., & Keogh, E. J. (2008). Querying and mining of time series data: Experimental comparison of representations and distance measures. PVLDB, 1(2), 1542–1552.Google Scholar
  3. Wilson, D. R., & Martinez, T. R. (2000). Reduction techniques for exemplar-based learning algorithms. Machine Learning, 38(3), 257–286.zbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Eamonn Keogh

There are no affiliations available