English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron

Kowalczyk, A., & Chapelle, O. (2005). An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron. In S. Jain, H. Simon, & E. Tomita (Eds.), Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8-11, 2005 (pp. 78-92). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-D3FD-9 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-0D9E-C
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007%2F11564089_8.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Kowalczyk, A, Author
Chapelle, O1, 2, Author           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: This paper deals with an unusual phenomenon where most machine learning algorithms yield good performance on the training set but systematically worse than random performance on the test set. This has been observed so far for some natural data sets and demonstrated for some synthetic data sets when the classification rule is learned from a small set of training samples drawn from some high dimensional space. The initial analysis presented in this paper shows that anti-learning is a property of data sets and is quite distinct from overfitting of a training data. Moreover, the analysis leads to a specification of some machine learning procedures which can overcome anti-learning and generate ma- chines able to classify training and test data consistently.

Details

show
hide
Language(s):
 Dates: 2005-10
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 3604
DOI: 10.1007/11564089_8
 Degree: -

Event

show
hide
Title: 16th International Conference on Algorithmic Learning Theory (ALT 2005)
Place of Event: Singapore
Start-/End Date: 2005-10-08 - 2005-10-11

Legal Case

show

Project information

show

Source 1

show
hide
Title: Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8-11, 2005
Source Genre: Proceedings
 Creator(s):
Jain, S, Editor
Simon, HU, Editor
Tomita, E, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 78 - 92 Identifier: ISBN: 978-3-540-29242-5

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 3734 Sequence Number: - Start / End Page: - Identifier: -