changeset 568:ae6ba0309bf9

nouveaux graphes
author Yoshua Bengio <bengioy@iro.umontreal.ca>
date Thu, 03 Jun 2010 13:19:16 -0400
parents 08709b62e574
children 9d01280ff1c1
files writeup/images/improvements_charts.pdf writeup/nips2010_submission.tex
diffstat 2 files changed, 3 insertions(+), 1 deletions(-) [+]
line wrap: on
line diff
Binary file writeup/images/improvements_charts.pdf has changed
--- a/writeup/nips2010_submission.tex	Thu Jun 03 13:16:53 2010 -0400
+++ b/writeup/nips2010_submission.tex	Thu Jun 03 13:19:16 2010 -0400
@@ -742,7 +742,9 @@
 The models are either trained on NIST (MLP0 and SDA0), 
 NISTP (MLP1 and SDA1), or P07 (MLP2 and SDA2), and tested
 on either NIST, NISTP or P07, either on the 62-class task
-or on the 10-digits task.
+or on the 10-digits task. Training (including about half
+for unsupervised pre-training, for DAs) on the larger
+datasets takes around one day on a GPU-285.
 Figure~\ref{fig:error-rates-charts} summarizes the results obtained,
 comparing humans, the three MLPs (MLP0, MLP1, MLP2) and the three SDAs (SDA0, SDA1,
 SDA2), along with the previous results on the digits NIST special database