CiteULike Search Register Log in
CiteULike is a free online bibliography manager. Register and you can start organising your references online.

Selection of relevant features and examples in machine learning

by: A. Blum
Artificial Intelligence, Vol. 97, No. 1-2. (December 1997), pp. 245-271.

X Abstract

In this survey, we review work in machine learning on methods for handling data sets containing large amounts of irrelevant information. We focus on two key issues: the problem of selecting relevant features, and the problem of selecting relevant examples. We describe the advances that have been made on these topics in both empirical and theoretical work in machine learning, and we present a general framework that we use to compare different methods. We close with some challenges for future work in this area.

View the full article here:

ACM, DOI, ElsevierPII, IngentaConnect

This article has been bookmarked 8 times, initially on 2005-11-20.

2009-07-13 User stharward
2009-05-08 User gr650
2008-12-01 User sirandreus , 1 note

There is no guarantee that just because a feature is relevant , it will be necessarily useful to an algorithm (and vice versa)

Notation

  • S is the sample set
  • D is the probability distribution of each element of S
  • c is the target function which maps an element from S to a class

Relevance to target 

Definition 1

A feature x_i is relevant to a target concept c if there exists a pair of examples A and B in the instance space such that A and B differ only in ther assignment to x_i and c(A) != c(B).


Relevance as a complexity measure (used in Winnow)

Measures complexity of the target function. Practical goal is not to identify an irrelevant subset of features, but to perform well when the complexity is low.

2008-12-01 21:42:42
2008-09-30 User misovalko
2008-05-14 User srp33
2008-04-09 User sona
2006-09-24 User sdvillal
2005-11-20 User yaroslavvb
Privacy Statement | Terms & Conditions
CiteULike organises scholarly (or academic) papers or literature and provides bibliographic (which means it makes bibliographies) for universities and higher education establishments. It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions. The service is similar in scope to EndNote or RefWorks or any other reference manager like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.