論文

査読有り
2021年

Random Number Generators in Training of Contextual Neural Networks.

Intelligent Information and Database Systems - 13th Asian Conference(ACIIDS)
  • Maciej Huk
  • ,
  • Kilho Shin
  • ,
  • Tetsuji Kuboyama
  • ,
  • Takako Hashimoto

12672 LNAI
開始ページ
717
終了ページ
730
記述言語
掲載種別
研究論文(国際会議プロシーディングス)
DOI
10.1007/978-3-030-73280-6_57
出版者・発行元
Springer

Much care should be given to the cases when there is a need to compare results of machine learning (ML) experiments performed with the usage of different Pseudo Random Number Generators (PRNGs). This is because the selection of PRNG can be regarded as a source of measurement error, e.g. in repeated N-fold Cross Validation (CV). It can be also important to verify if the observed properties of a model or algorithm are not due to the effects of the use of a particular PRNG. In this paper we conduct experiments so that we can observe the possible level of differences in obtained values of various measures of classification quality of simple Contextual Neural Networks and Multilayer Perceptron (MLP) models for various PRNGs. It is presented that the results for some pairs of PRNGs can be significantly different even for large number of repeats of 5-fold CV. Observations suggest that when different ML models and algorithms are compared with the usage of 5-fold CV when different PRNGs were used, the confidence interval should be doubled or confidence level higher than 95% should be used. Additionally, it is shown that even under such conditions classification properties of Contextual Neural Networks are found statistically better than of not-contextual MLP models.

リンク情報
DOI
https://doi.org/10.1007/978-3-030-73280-6_57
DBLP
https://dblp.uni-trier.de/rec/conf/aciids/HukSKH21
URL
https://dblp.uni-trier.de/rec/conf/aciids/2021
URL
https://dblp.uni-trier.de/db/conf/aciids/aciids2021.html#HukSKH21
Scopus
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85104817997&origin=inward
Scopus Citedby
https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85104817997&origin=inward
ID情報
  • DOI : 10.1007/978-3-030-73280-6_57
  • ISSN : 0302-9743
  • eISSN : 1611-3349
  • ISBN : 9783030732790
  • ISBN : 9783030732806
  • DBLP ID : conf/aciids/HukSKH21
  • SCOPUS ID : 85104817997

エクスポート
BibTeX RIS