Some notes on neural learning algorithm benchmarking

New neural learning algorithms are often benchmarked only poorly. This article gathers some important DOs and DON'Ts for researchers in order to improve on that situation. The essential requirements are (1) Volume: benchmarking has to be broad enough, i.e. must use several problems; (2) Validit...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 9; no. 3; pp. 343 - 347
Main Author Prechelt, Lutz
Format Journal Article
LanguageEnglish
Published Elsevier B.V 1995
Subjects
Benchmarks
Comparability
Methodology
Reproducibility
Validity
Benchmarks
Validity
Comparability
Methodology
Reproducibility
Online AccessGet full text
ISSN0925-2312
1872-8286
DOI10.1016/0925-2312(95)00084-1

Cover

More Information
Summary:New neural learning algorithms are often benchmarked only poorly. This article gathers some important DOs and DON'Ts for researchers in order to improve on that situation. The essential requirements are (1) Volume: benchmarking has to be broad enough, i.e. must use several problems; (2) Validity: common errors that invalidate the results have to be avoided; (3) Reproducibility: benchmarking has to be documented well enough to be completely reproducible; and (4) Comparability: benchmark results should, if possible, be directly comparable with the results achieved by others using different algorithms.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0925-2312
1872-8286
DOI:10.1016/0925-2312(95)00084-1