# HG changeset patch
# User Yoshua Bengio <bengioy@iro.umontreal.ca>
# Date 1275415502 14400
# Node ID 66a905508e34fc01f1e249d33ea5a5c39e1f8230
# Parent  6f042a71be239e9b4dac9e2b1e2816fb5e2b967a# Parent  8c2ab4f246b19be8d62c02fa4b2ff50a9f35242e
resolved merge conflict

diff -r 8c2ab4f246b1 -r 66a905508e34 writeup/nips2010_submission.tex
--- a/writeup/nips2010_submission.tex	Tue Jun 01 10:59:47 2010 -0700
+++ b/writeup/nips2010_submission.tex	Tue Jun 01 14:05:02 2010 -0400
@@ -90,6 +90,10 @@
 of {\em out-of-distribution} examples and of the multi-task setting
 (but see~\citep{CollobertR2008}). In particular the {\em relative
 advantage} of deep learning for this settings has not been evaluated.
+The hypothesis explored here is that a deep hierarchy of features
+may be better able to provide sharing of statistical strength
+between different regions in input space or different tasks,
+as discussed in the conclusion.
 
 In this paper we ask the following questions: