Mercurial > ift6266
changeset 461:9609c5cf9b6b
lit. results
author | Yoshua Bengio <bengioy@iro.umontreal.ca> |
---|---|
date | Fri, 28 May 2010 07:48:14 -0600 |
parents | fe292653a0f8 |
children | f59af1648d83 |
files | writeup/techreport.tex |
diffstat | 1 files changed, 6 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/writeup/techreport.tex Thu May 27 21:53:24 2010 -0600 +++ b/writeup/techreport.tex Fri May 28 07:48:14 2010 -0600 @@ -380,7 +380,8 @@ \{SDA,MLP\}0 are trained on NIST, \{SDA,MLP\}1 are trained on NISTP, and \{SDA,MLP\}2 are trained on P07. The human error rate on digits is a lower bound because it does not count digits that were -recognized as letters.} +recognized as letters. For comparison, the results found in the literature +on NIST digits classification using the same test set are included.} \label{tab:sda-vs-mlp-vs-humans} \begin{center} \begin{tabular}{|l|r|r|r|r|} \hline @@ -392,6 +393,10 @@ MLP0 & 24.2\% $\pm$.15\% & 68.8\%$\pm$.33\% & 78.70\%$\pm$.14\% & 3.45\% $\pm$.15\% \\ \hline MLP1 & 23.0\% $\pm$.15\% & 41.8\%$\pm$.35\% & 90.4\%$\pm$.1\% & 3.85\% $\pm$.16\% \\ \hline MLP2 & 24.3\% $\pm$.15\% & 46.0\%$\pm$.35\% & 54.7\%$\pm$.17\% & 4.85\% $\pm$.18\% \\ \hline +[5] & & & & 4.95\% $\pm$.18\% \\ \hline +[2] & & & & 3.71\% $\pm$.16\% \\ \hline +[3] & & & & 2.4\% $\pm$.13\% \\ \hline +[4] & & & & 2.1\% $\pm$.12\% \\ \hline \end{tabular} \end{center} \end{table}