Počet záznamů: 1
Advances in Pattern Recognition Research
- 1.
SYSNO ASEP 0497831 Druh ASEP M - Kapitola v monografii Zařazení RIV C - Kapitola v knize Název A Statistical Review of the MNIST Benchmark Data Problem Tvůrce(i) Grim, Jiří (UTIA-B) RID, ORCID
Somol, Petr (UTIA-B) RIDCelkový počet autorů 2 Zdroj.dok. Advances in Pattern Recognition Research, A Statistical Review of the MNIST Benchmark Data Problem. - New York : Nova Science Publishers, Inc., 2018 / Lu T. ; Chao T.H. - ISBN 978-1-53614-429-1 Rozsah stran s. 172-193 Poč.str. 19 s. Poč.str.knihy 272 Forma vydání Tištěná - P Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova MNIST benchmark ; multivariate Bernoulli mixtures ; EM algorithm Vědní obor RIV IN - Informatika Obor OECD Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) CEP GA17-18407S GA ČR - Grantová agentura ČR Institucionální podpora UTIA-B - RVO:67985556 EID SCOPUS 85061142387 Anotace The recognition of MNIST numerals is discussed as a benchmark problem. Applying the probabilistic neural networks to MNIST data we have found that the training and test set have slightly different statistical properties with negative consequences for classifier performance. We assume that the frequently used extension of MNIST training data by distorted patterns improves the recognition accuracy by creating images similar to the atypical test set numerals. In this way the benchmark experiments may be influenced by the external knowledge about the hand-written digits and the comparative value of the benchmark becomes more or less limited to recognition of MNIST numerals. As a more generally applicable benchmark model we propose recognition of artificial binary patterns generated on a chessboard by random moves of the pieces rook and knight. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2019
Počet záznamů: 1