Mercurial > ift6266
comparison writeup/nips2010_submission.tex @ 487:21787ac4e5a0
-
| author | Yoshua Bengio <bengioy@iro.umontreal.ca> |
|---|---|
| date | Mon, 31 May 2010 22:04:44 -0400 |
| parents | 877af97ee193 |
| children | ee9836baade3 d6cf4912abb0 |
comparison
equal
deleted
inserted
replaced
| 486:877af97ee193 | 487:21787ac4e5a0 |
|---|---|
| 564 \section{Conclusions} | 564 \section{Conclusions} |
| 565 \vspace*{-1mm} | 565 \vspace*{-1mm} |
| 566 | 566 |
| 567 The conclusions are positive for all the questions asked in the introduction. | 567 The conclusions are positive for all the questions asked in the introduction. |
| 568 %\begin{itemize} | 568 %\begin{itemize} |
| 569 | |
| 569 $\bullet$ %\item | 570 $\bullet$ %\item |
| 570 Do the good results previously obtained with deep architectures on the | 571 Do the good results previously obtained with deep architectures on the |
| 571 MNIST digits generalize to the setting of a much larger and richer (but similar) | 572 MNIST digits generalize to the setting of a much larger and richer (but similar) |
| 572 dataset, the NIST special database 19, with 62 classes and around 800k examples? | 573 dataset, the NIST special database 19, with 62 classes and around 800k examples? |
| 573 Yes, the SDA systematically outperformed the MLP and all the previously | 574 Yes, the SDA systematically outperformed the MLP and all the previously |