--- a/writeup/nips2010_submission.tex	Tue Jun 01 16:06:32 2010 -0400
+++ b/writeup/nips2010_submission.tex	Tue Jun 01 14:06:43 2010 -0700
@@ -688,6 +688,16 @@
 it was very significant for the SDA (from +13\% to +27\% relative change).
 %\end{itemize}
 
+In the original self-taught learning framework~\citep{RainaR2007}, the
+out-of-sample examples were used as a source of unsupervised data, and
+experiments showed its positive effects in a \emph{limited labeled data}
+scenario. However, many of the results by \citet{RainaR2007} (who used a
+shallow, sparse coding approach) suggest that the relative gain of self-taught
+learning diminishes as the number of labeled examples increases, (essentially,
+a ``diminishing returns'' scenario occurs).  We note that, for deep
+architectures, our experiments show that such a positive effect is accomplished
+even in a scenario with a \emph{very large number of labeled examples}.
+
 Why would deep learners benefit more from the self-taught learning framework?
 The key idea is that the lower layers of the predictor compute a hierarchy
 of features that can be shared across tasks or across variants of the