--- a/writeup/nips2010_submission_supplementary.tex	Thu Jun 03 08:09:35 2010 -0400
+++ b/writeup/nips2010_submission_supplementary.tex	Thu Jun 03 08:14:08 2010 -0400
@@ -16,9 +16,10 @@
 
 \section*{Appendix I: Full results}
 
-These tables correspond to Figures 3 and 4 and contain the raw error rates for each model and dataset considered.
+These tables correspond to Figures 2 and 3 and contain the raw error rates for each model and dataset considered.
+They also contain additional data such as test errors on P07 and standard errors.
 
-\begin{table}[h]
+\begin{table}[ht]
 \caption{Overall comparison of error rates ($\pm$ std.err.) on 62 character classes (10 digits +
 26 lower + 26 upper), except for last columns -- digits only, between deep architecture with pre-training
 (SDA=Stacked Denoising Autoencoder) and ordinary shallow architecture 
@@ -48,7 +49,7 @@
 \end{center}
 \end{table}
 
-\begin{table}[h]
+\begin{table}[ht]
 \caption{Relative change in error rates due to the use of perturbed training data,
 either using NISTP, for the MLP1/SDA1 models, or using P07, for the MLP2/SDA2 models.
 A positive value indicates that training on the perturbed data helped for the
@@ -69,7 +70,7 @@
 \end{center}
 \end{table}
 
-\begin{table}[h]
+\begin{table}[ht]
 \caption{Test error rates and relative change in error rates due to the use of
 a multi-task setting, i.e., training on each task in isolation vs training
 for all three tasks together, for MLPs vs SDAs. The SDA benefits much
@@ -91,11 +92,15 @@
 \end{center}
 \end{table}
 
-{\small
+
+\newpage
+
+\vspace*{10mm}
+%{\small
 \bibliography{strings,strings-short,strings-shorter,ift6266_ml,aigaion-shorter,specials}
 %\bibliographystyle{plainnat}
 \bibliographystyle{unsrtnat}
 %\bibliographystyle{apalike}
-}
+%}
 
 \end{document}