Advances in Pattern Recognition Research

0497831 - ÚTIA 2019 RIV US eng M - Monography Chapter
Grim, Jiří - Somol, Petr
A Statistical Review of the MNIST Benchmark Data Problem.
Advances in Pattern Recognition Research. New York: Nova Science Publishers, Inc., 2018 - (Lu, T.; Chao, T.), s. 172-193. ISBN 978-1-53614-429-1
R&D Projects: GA ČR GA17-18407S
Institutional support: RVO:67985556
Keywords : MNIST benchmark * multivariate Bernoulli mixtures * EM algorithm
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://library.utia.cas.cz/separaty/2018/RO/grim-0497831.pdf

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.
Permanent Link: http://hdl.handle.net/11104/0290648