| bibtype |
M -
Monography Chapter
|
| ARLID |
0497831 |
| utime |
20240103221057.7 |
| mtime |
20181210235959.9 |
| SCOPUS |
85061142387 |
| title
(primary) (eng) |
A Statistical Review of the MNIST Benchmark Data Problem |
| specification |
| book_pages |
272 |
| page_count |
19 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0497830 |
| ISBN |
978-1-53614-429-1 |
| title
|
Advances in Pattern Recognition Research |
| part_title |
A Statistical Review of the MNIST Benchmark Data Problem |
| page_num |
172-193 |
| publisher |
| place |
New York |
| name |
Nova Science Publishers, Inc. |
| year |
2018 |
|
| editor |
|
| editor |
|
|
| keyword |
MNIST benchmark |
| keyword |
multivariate Bernoulli mixtures |
| keyword |
EM algorithm |
| author
(primary) |
| ARLID |
cav_un_auth*0101091 |
| full_dept |
Department of Pattern Recognition |
| share |
50 |
| name1 |
Grim |
| name2 |
Jiří |
| institution |
UTIA-B |
| full_dept (cz) |
Rozpoznávání obrazu |
| full_dept (eng) |
Department of Pattern Recognition |
| department (cz) |
RO |
| department (eng) |
RO |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0101197 |
| full_dept |
Department of Pattern Recognition |
| share |
50 |
| name1 |
Somol |
| name2 |
Petr |
| institution |
UTIA-B |
| full_dept (cz) |
Rozpoznávání obrazu |
| full_dept |
Department of Pattern Recognition |
| department (cz) |
RO |
| department |
RO |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| ARLID |
cav_un_auth*0347019 |
| project_id |
GA17-18407S |
| agency |
GA ČR |
|
| abstract
(eng) |
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. |
| RIV |
IN |
| FORD0 |
10000 |
| FORD1 |
10200 |
| FORD2 |
10201 |
| reportyear |
2019 |
| num_of_auth |
2 |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0290648 |
| confidential |
S |
| arlyear |
2018 |
| mrcbU14 |
85061142387 SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
WOS |
| mrcbU63 |
cav_un_epca*0497830 Advances in Pattern Recognition Research A Statistical Review of the MNIST Benchmark Data Problem Nova Science Publishers, Inc. 2018 New York 172 193 978-1-53614-429-1 |
| mrcbU67 |
340 Lu T. |
| mrcbU67 |
340 Chao T.H. |
|