NN Classifiers: Reducing the Computational Cost of Cross-Validation by Active Pattern Selection

Dunedin, New Zealand November 20-November 23

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/ANNES.1995.499447

2nd New Zealand Two-Stream Internatio ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Friedrich Leisch Articles by Kurt Hornik Articles by Lakhmi C. Jain

	ASCII Text	x
	Friedrich Leisch, Kurt Hornik, Lakhmi C. Jain, "NN Classifiers: Reducing the Computational Cost of Cross-Validation by Active Pattern Selection," Artificial Neural Networks and Expert Systems, New Zealand Conference, pp. 91, 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems (ANNES '95), 1995.

	BibTex	x
	@article{ 10.1109/ANNES.1995.499447, author = {Friedrich Leisch and Kurt Hornik and Lakhmi C. Jain}, title = {NN Classifiers: Reducing the Computational Cost of Cross-Validation by Active Pattern Selection}, journal ={Artificial Neural Networks and Expert Systems, New Zealand Conference}, volume = {0}, year = {1995}, isbn = {0-8186-7174-2}, pages = {91}, doi = {http://doi.ieeecomputersociety.org/10.1109/ANNES.1995.499447}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Artificial Neural Networks and Expert Systems, New Zealand Conference TI - NN Classifiers: Reducing the Computational Cost of Cross-Validation by Active Pattern Selection SN - 0-8186-7174-2 SP EP A1 - Friedrich Leisch, A1 - Kurt Hornik, A1 - Lakhmi C. Jain, PY - 1995 KW - ANNES'95 KW - Neural Networks KW - Classification KW - Cross-Validation KW - Leave-one-out KW - Computational Cost VL - 0 JA - Artificial Neural Networks and Expert Systems, New Zealand Conference ER -

Friedrich Leisch, Institut fnr Statistik und Wahrscheinlichkeitstheorie

Kurt Hornik, Institut fnr Statistik und Wahrscheinlichkeitstheorie

Lakhmi C. Jain, University of South Australia

We propose a new approach for leave-one-out cross-validation of neural network classifiers called "cross-validation with active pattern selection" (CV/APS). In CV/APS, the contribution of the training patterns to back-propagation learning is estimated and this information is used for active selection of CV patterns. On two artificial examples, the computational cost of CV can be reduced to 25% of the normal costs with only small or no errors.

Index Terms:

ANNES'95, Neural Networks, Classification, Cross-Validation, Leave-one-out, Computational Cost

Citation:

Friedrich Leisch, Kurt Hornik, Lakhmi C. Jain, "NN Classifiers: Reducing the Computational Cost of Cross-Validation by Active Pattern Selection," annes, pp.91, 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems (ANNES '95), 1995

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.