LIMITED DISTRIBUTION NOTICE: This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g. , payment of royalties). Copies may be requested from IBM T. J. Definition A learning curve shows a measure of predictive performance on a given domain as a function of some measure of varying amounts of learning effort. The most common form of learning curves in the general field of machine learning shows predictive accuracy on the test examples as a function of the number of training examples as in Figure 1. Figure 1: Stylized learning curve showing the model accuracy on test examples as function of the number of training examples.
[1]
T. P. Wright,et al.
Factors affecting the cost of airplanes
,
1936
.
[2]
Bernhard W. Flury,et al.
Error rates in quadratic discrimination with constraints on the covariance matrices
,
1994
.
[3]
Jeffrey S. Simonoff,et al.
Tree Induction Vs Logistic Regression: A Learning Curve Analysis
,
2001,
J. Mach. Learn. Res..
[4]
Pat Langley,et al.
Machine learning as an experimental science
,
2004,
Machine Learning.
[5]
Raymond J. Mooney,et al.
Symbolic and neural learning algorithms: An experimental comparison
,
1991,
Machine Learning.
[6]
Lawrence D. Jackel,et al.
Learning Curves: Asymptotic Values and Rate of Convergence
,
1993,
NIPS.