Presenting and analyzing the results of AI experiments: data averaging and data snooping

C. Lee Giles, Steve Lawrence

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The common processes of data averaging and data snooping are evaluated in the context of neural networks. It is shown that both processes can lead to misleading results. Techniques are proposed for avoiding these problems. New guidelines for reporting performance are also recommended. These guidelines provide information about the actual distribution.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
Editors Anon
PublisherAAAI
Pages362-367
Number of pages6
StatePublished - 1997
EventProceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97 - Providence, RI, USA
Duration: Jul 27 1997Jul 31 1997

Other

OtherProceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97
CityProvidence, RI, USA
Period7/27/977/31/97

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Presenting and analyzing the results of AI experiments: data averaging and data snooping'. Together they form a unique fingerprint.

  • Cite this

    Giles, C. L., & Lawrence, S. (1997). Presenting and analyzing the results of AI experiments: data averaging and data snooping. In Anon (Ed.), Proceedings of the National Conference on Artificial Intelligence (pp. 362-367). AAAI.