PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron
Adam Kowalczyk and Olivier Chapelle
In: Algorithmic Learning Theory, Singapore(2005).

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 over-fitting 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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:1154
Deposited By:Olivier Chapelle
Deposited On:18 November 2005