# HG changeset patch # User Yoshua Bengio # Date 1301000705 14400 # Node ID e63d23c7c9fb0c92440de120dce044397d62e56d # Parent 24d9819a810f6f67863615c1dd943cea7a861058# Parent 8b1a0b9fecff8bba03b1188d87c7a54bf8b27c3e reviews aistats finales diff -r 24d9819a810f -r e63d23c7c9fb writeup/Makefile --- a/writeup/Makefile Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/Makefile Thu Mar 24 17:05:05 2011 -0400 @@ -1,7 +1,7 @@ all: aistats2011_cameraready.pdf #all: nips2010_submission.pdf -%.pdf: %.tex images/* +%.pdf: %.tex images/* *.bib pdflatex $< bibtex -min-crossrefs=999 ${<:.tex=} pdflatex $< diff -r 24d9819a810f -r e63d23c7c9fb writeup/aistats2011_cameraready.tex --- a/writeup/aistats2011_cameraready.tex Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/aistats2011_cameraready.tex Thu Mar 24 17:05:05 2011 -0400 @@ -273,7 +273,7 @@ the MNIST digits task~\citep{Hinton06,ranzato-07-small,Bengio-nips-2006,Salakhutdinov+Hinton-2009}, with 60,000 examples, and variants involving 10,000 examples~\citep{Larochelle-jmlr-2009,VincentPLarochelleH2008-very-small}\footnote{Fortunately, there -are more and more exceptions of course, such as~\citet{RainaICML09} using a million examples.} +are more and more exceptions of course, such as~\citet{RainaICML09-small} using a million examples.} The focus here is on much larger training sets, from 10 times to to 1000 times larger, and 62 classes. @@ -328,13 +328,13 @@ {\bf NIST.} Our main source of characters is the NIST Special Database 19~\citep{Grother-1995}, widely used for training and testing character -recognition systems~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005}. +recognition systems~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005}. The dataset is composed of 814255 digits and characters (upper and lower cases), with hand checked classifications, extracted from handwritten sample forms of 3600 writers. The characters are labelled by one of the 62 classes corresponding to ``0''-``9'',``A''-``Z'' and ``a''-``z''. The dataset contains 8 parts (partitions) of varying complexity. The fourth partition (called $hsf_4$, 82,587 examples), experimentally recognized to be the most difficult one, is the one recommended -by NIST as a testing set and is used in our work as well as some previous work~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005} +by NIST as a testing set and is used in our work as well as some previous work~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005} for that purpose. We randomly split the remainder (731,668 examples) into a training set and a validation set for model selection. The performances reported by previous work on that dataset mostly use only the digits. @@ -575,7 +575,7 @@ on NIST, 1 on NISTP, and 2 on P07. Left: overall results of all models, on NIST and NISTP test sets. Right: error rates on NIST test digits only, along with the previous results from -literature~\citep{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002-short,Milgram+al-2005} +literature~\citep{Granger+al-2007,Cortes+al-2000-small,Oliveira+al-2002-short,Milgram+al-2005} respectively based on ART, nearest neighbors, MLPs, and SVMs.} \label{fig:error-rates-charts} %\vspace*{-2mm} @@ -616,7 +616,7 @@ SDA2), along with the previous results on the digits NIST special database 19 test set from the literature, respectively based on ARTMAP neural networks ~\citep{Granger+al-2007}, fast nearest-neighbor search -~\citep{Cortes+al-2000}, MLPs ~\citep{Oliveira+al-2002-short}, and SVMs +~\citep{Cortes+al-2000-small}, MLPs ~\citep{Oliveira+al-2002-short}, and SVMs ~\citep{Milgram+al-2005}.% More detailed and complete numerical results %(figures and tables, including standard errors on the error rates) can be %found in Appendix. @@ -830,7 +830,7 @@ MLP1 & 23.0\% $\pm$.15\% & 41.8\%$\pm$.35\% & 90.4\%$\pm$.1\% & 3.85\% $\pm$.16\% \\ \hline MLP2 & 24.3\% $\pm$.15\% & 46.0\%$\pm$.35\% & 54.7\%$\pm$.17\% & 4.85\% $\pm$.18\% \\ \hline \citep{Granger+al-2007} & & & & 4.95\% $\pm$.18\% \\ \hline -\citep{Cortes+al-2000} & & & & 3.71\% $\pm$.16\% \\ \hline +\citep{Cortes+al-2000-small} & & & & 3.71\% $\pm$.16\% \\ \hline \citep{Oliveira+al-2002} & & & & 2.4\% $\pm$.13\% \\ \hline \citep{Milgram+al-2005} & & & & 2.1\% $\pm$.12\% \\ \hline \end{tabular} diff -r 24d9819a810f -r e63d23c7c9fb writeup/ift6266_ml.bib --- a/writeup/ift6266_ml.bib Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/ift6266_ml.bib Thu Mar 24 17:05:05 2011 -0400 @@ -10612,10 +10612,10 @@ @InProceedings{icml2009_093, author = {Hossein Mobahi and Ronan Collobert and Jason Weston}, title = {Deep Learning from Temporal Coherence in Video}, - booktitle = {Proceedings of the 26th International Conference on Machine Learning}, + booktitle = ICML09, pages = {737--744}, year = 2009, - editor = {L\'{e}on Bottou and Michael Littman}, + editor = ICML09ed, address = {Montreal}, month = {June}, publisher = {Omnipress} @@ -10894,7 +10894,7 @@ original = "orig/jarrett-iccv-09.pdf", title = "What is the Best Multi-Stage Architecture for Object Recognition?", author = "Jarrett, Kevin and Kavukcuoglu, Koray and Ranzato, {Marc'Aurelio} and {LeCun}, Yann", - booktitle = "Proc. International Conference on Computer Vision (ICCV'09)", + booktitle = ICCV09, publisher = "IEEE", year = "2009" } @@ -17826,6 +17826,19 @@ address = {New York, NY, USA}, } +@inproceedings{RainaICML09-small, + author = {Raina, Rajat and Madhavan, Anand and Ng, Andrew Y.}, + title = {Large-scale deep unsupervised learning using graphics processors}, + booktitle = ICML09, + editor = ICML09ed, + publisher = ICML09publ, + year = {2009}, + isbn = {978-1-60558-516-1}, + pages = {873--880}, + location = {Montreal, Quebec, Canada}, + address = {New York, NY, USA}, +} + @InProceedings{Ramanujam88, author = "J. Ramanujam and P. Sadayappan", booktitle = icnn, @@ -21402,7 +21415,7 @@ @inproceedings{Taylor-cvpr-2010, author = {Graham Taylor and Leonid Sigal and David Fleet and Geoffrey Hinton}, title = {Dynamic binary latent variable models for {3D} pose tracking}, - booktitle = {Proc. Conference on Computer Vision and Pattern Recognition (CVPR'2010)}, + booktitle = cvpr10, year = 2010, } @@ -21416,10 +21429,10 @@ @InProceedings{TaylorHintonICML2009, author = {Graham Taylor and Geoffrey Hinton}, title = {Factored Conditional Restricted {Boltzmann} Machines for Modeling Motion Style}, - booktitle = {Proceedings of the 26th International Conference on Machine Learning (ICML'09)}, + booktitle = ICML09, pages = {1025--1032}, year = 2009, - editor = {L\'{e}on Bottou and Michael Littman}, + editor = ICML09ed, address = {Montreal}, month = {June}, publisher = {Omnipress} @@ -23124,10 +23137,10 @@ @InProceedings{MobahiCollobertWestonICML2009, author = {Hossein Mobahi and Ronan Collobert and Jason Weston}, title = {Deep Learning from Temporal Coherence in Video}, - booktitle = {Proceedings of the 26th International Conference on Machine Learning}, + booktitle = ICML09, pages = {737--744}, year = 2009, - editor = {L\'{e}on Bottou and Michael Littman}, + editor = ICML09ed, address = {Montreal}, month = {June}, publisher = {Omnipress} @@ -25716,6 +25729,16 @@ address = {London, UK}, } +@inproceedings{Cortes+al-2000-small, + author = {Juan Carlos P\'{e}rez-Cortes and Rafael Llobet and Joaquim Arlandis}, + title = {Fast and Accurate Handwritten Character Recognition Using Approximate Nearest Neighbours Search on Large Databases}, + booktitle = iapr, + year = {2000}, + pages = {767--776}, + publisher = {Springer-Verlag}, + address = {London, UK}, + } + @Article{Oliveira+al-2002, author = "Oliveira, L.S. and Sabourin, R. and Bortolozzi, F. and Suen, C.Y.", diff -r 24d9819a810f -r e63d23c7c9fb writeup/strings-short.bib --- a/writeup/strings-short.bib Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/strings-short.bib Thu Mar 24 17:05:05 2011 -0400 @@ -2,6 +2,8 @@ @String{AI06 = "AI 2006"} +@String{ICCV09 = "ICCV 2009"} + @String{JSM02="Proc. of JSM 2002"} @STRING{NIPS = "NIPS"} @@ -214,6 +216,7 @@ @String{cvpr07 = "Proc. {CVPR}'07"} @String{cvpr08 = "Proc. {CVPR}'08"} @String{cvpr09 = "Proc. {CVPR}'09"} +@String{cvpr10 = "Proc. {CVPR}'10"} @string{IEEE_trans_biomed = "{IEEE} Trans. Biomed. Eng."} @string{IJCAS = "{IJCAS}"} diff -r 24d9819a810f -r e63d23c7c9fb writeup/strings-shorter.bib --- a/writeup/strings-shorter.bib Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/strings-shorter.bib Thu Mar 24 17:05:05 2011 -0400 @@ -2,6 +2,8 @@ @String{AI06 = "AI 2006"} +@String{ICCV09 = "ICCV'09"} + @String{JSM02="Proc. of JSM 2002"} @STRING{NIPS = "NIPS"} @@ -81,20 +83,20 @@ @String{ICDAR03 = "Proc. {ICDAR}'03"} @String{ICDAR07 = "Proc. {ICDAR}'07"} -@String{ICML96 = "{ICML}"} -@String{ICML97 = "{ICML}"} -@String{ICML98 = "{ICML}"} -@String{ICML99 = "{ICML}"} -@String{ICML00 = "{ICML}"} -@String{ICML01 = "{ICML}"} -@String{ICML02 = "{ICML}"} -@String{ICML03 = "{ICML}"} -@String{ICML04 = "{ICML}"} -@String{ICML05 = "{ICML}"} -@String{ICML06 = "{ICML}"} -@String{ICML07 = "{ICML}"} -@String{ICML08 = "{ICML}"} -@String{ICML09 = "{ICML}"} +@String{ICML96 = "{ICML} 1996"} +@String{ICML97 = "{ICML} 1997"} +@String{ICML98 = "{ICML} 1998"} +@String{ICML99 = "{ICML} 1999"} +@String{ICML00 = "{ICML} 2000"} +@String{ICML01 = "{ICML} 2001"} +@String{ICML02 = "{ICML} 2002"} +@String{ICML03 = "{ICML} 2003"} +@String{ICML04 = "{ICML} 2004"} +@String{ICML05 = "{ICML} 2005"} +@String{ICML06 = "{ICML} 2006"} +@String{ICML07 = "{ICML} 2007"} +@String{ICML08 = "{ICML} 2008"} +@String{ICML09 = "{ICML} 2009"} @string{icml09loc = {}} @STRING{aistats05 = "AISTATS'2005"} @STRING{aistats07 = "AISTATS'2007"} diff -r 24d9819a810f -r e63d23c7c9fb writeup/strings.bib --- a/writeup/strings.bib Thu Mar 24 17:04:38 2011 -0400 +++ b/writeup/strings.bib Thu Mar 24 17:05:05 2011 -0400 @@ -42,6 +42,7 @@ @STRING{aistats07-small = "Proceedings of AISTATS-2007"} @STRING{aistats09 = "Proceedings of The Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS'09)"} +@STRING{aistats10 = "Proceedings of The Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS'10)"} @String{ams = "Ann. Math. Stat."} @@ -103,6 +104,7 @@ @String{cvpr07 = "Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR'07)"} @String{cvpr08 = "Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR'08)"} @String{cvpr09 = "Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR'09)"} +@String{cvpr10 = "Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR'10)!!!!"} @String{DIRO= "D\'epartement d'informatique et recherche op\'erationnelle, Universit\'e de Montr\'eal"} @@ -137,6 +139,8 @@ @String{ICCV07 = "Proceedings {IEEE} of the 11th International Conference on Computer Vision (ICCV'07)"} +@String{ICCV09 = "Proceedings {IEEE} International Conference on Computer Vision (ICCV'09)"} + @String{ICDAR95 = "3rd International Conference on Document Analysis and Recognition (ICDAR'95)"} @String{ICDAR03 = "International Conference on Document Analysis and Recognition (ICDAR'03)"} @@ -379,7 +383,7 @@ @String{ICML07ed = {Zoubin Ghahramani}} @String{ICML07publ = "ACM"} -@String{ICML08 = "Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML'08)"} +@String{ICML08 = "Proceedings of the Twenty-fifth International Conference on Machine Learning ({ICML}'08)"} @String{ICML08ed = "William W. Cohen and Andrew McCallum and Sam T. Roweis"} @String{ICML08publ = "ACM"} @@ -388,6 +392,13 @@ @String{ICML09publ = "ACM"} @string{icml09loc = {Montreal, Quebec, Canada}} + +@String{ICML10 = "Proceedings of the Twenty-seventh International Conference on Machine Learning (ICML-10)"} +@String{ICML10ed = {L\'{e}on Bottou and Michael Littman}} +@String{ICML10publ = "ACM"} +@string{icml10loc = {Haifa, Israel}} + + @String{nipc-hmit96 = "The 1996 American Nuclear Society International Topical Meeting on Nuclear Plant Instrumentation, Control and Human Machine Interface Technologies"} @String{nn = "Neural Networks"} @@ -474,4 +485,4 @@ @string{DMKD = "Data Mining and Knowledge Discovery"} @string{IEEE_trans_NN = "IEEE Transactions on Neural Networks"} @string{eng_med_bio = "Engineering in Medicine and Biology Magazine, IEEE"} -@string{ICTAI06 = "IEEE International Conference on Tools with Artificial Intelligence"} \ No newline at end of file +@string{ICTAI06 = "IEEE International Conference on Tools with Artificial Intelligence"}