--- a/writeup/aistats2011_cameraready.tex	Mon Mar 21 11:28:42 2011 -0400
+++ b/writeup/aistats2011_cameraready.tex	Mon Mar 21 11:29:09 2011 -0400
@@ -273,7 +273,7 @@
 the MNIST digits task~\citep{Hinton06,ranzato-07-small,Bengio-nips-2006,Salakhutdinov+Hinton-2009},
 with 60,000 examples, and variants involving 10,000
 examples~\citep{Larochelle-jmlr-2009,VincentPLarochelleH2008-very-small}\footnote{Fortunately, there
-are more and more exceptions of course, such as~\citet{RainaICML09} using a million examples.}
+are more and more exceptions of course, such as~\citet{RainaICML09-small} using a million examples.}
 The focus here is on much larger training sets, from 10 times to 
 to 1000 times larger, and 62 classes.
 
@@ -328,13 +328,13 @@
 {\bf NIST.}
 Our main source of characters is the NIST Special Database 19~\citep{Grother-1995}, 
 widely used for training and testing character
-recognition systems~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005}. 
+recognition systems~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005}. 
 The dataset is composed of 814255 digits and characters (upper and lower cases), with hand checked classifications,
 extracted from handwritten sample forms of 3600 writers. The characters are labelled by one of the 62 classes 
 corresponding to ``0''-``9'',``A''-``Z'' and ``a''-``z''. The dataset contains 8 parts (partitions) of varying complexity. 
 The fourth partition (called $hsf_4$, 82,587 examples), 
 experimentally recognized to be the most difficult one, is the one recommended 
-by NIST as a testing set and is used in our work as well as some previous work~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005}
+by NIST as a testing set and is used in our work as well as some previous work~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005}
 for that purpose. We randomly split the remainder (731,668 examples) into a training set and a validation set for
 model selection. 
 The performances reported by previous work on that dataset mostly use only the digits.
@@ -575,7 +575,7 @@
 on NIST, 1 on NISTP, and 2 on P07. Left: overall results
 of all models, on NIST and NISTP test sets.
 Right: error rates on NIST test digits only, along with the previous results from 
-literature~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005}
+literature~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005}
 respectively based on ART, nearest neighbors, MLPs, and SVMs.}
 \label{fig:error-rates-charts}
 %\vspace*{-2mm}
@@ -616,7 +616,7 @@
 SDA2), along with the previous results on the digits NIST special database
 19 test set from the literature, respectively based on ARTMAP neural
 networks ~\citep{Granger+al-2007}, fast nearest-neighbor search
-~\citep{Cortes+al-2000}, MLPs ~\citep{Oliveira+al-2002-short}, and SVMs
+~\citep{Cortes+al-2000-small}, MLPs ~\citep{Oliveira+al-2002-short}, and SVMs
 ~\citep{Milgram+al-2005}.%  More detailed and complete numerical results
 %(figures and tables, including standard errors on the error rates) can be
 %found in Appendix.
@@ -830,7 +830,7 @@
 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 
 \citep{Granger+al-2007} &     &                    &                   & 4.95\% $\pm$.18\% \\ \hline
-\citep{Cortes+al-2000} &      &                    &                   & 3.71\% $\pm$.16\% \\ \hline
+\citep{Cortes+al-2000-small} &      &                    &                   & 3.71\% $\pm$.16\% \\ \hline
 \citep{Oliveira+al-2002} &    &                    &                   & 2.4\% $\pm$.13\% \\ \hline
 \citep{Milgram+al-2005} &      &                    &                   & 2.1\% $\pm$.12\% \\ \hline
 \end{tabular}