# HG changeset patch # User Xavier Glorot # Date 1275260722 14400 # Node ID 150203d2b5c312e599c74809000e5f28fa7a0f6b # Parent 6593e67381a302a9dffe5fb1112f5c071601e43d added number of train test and valid for NIST diff -r 6593e67381a3 -r 150203d2b5c3 writeup/nips2010_submission.tex --- a/writeup/nips2010_submission.tex Sun May 30 18:54:36 2010 -0400 +++ b/writeup/nips2010_submission.tex Sun May 30 19:05:22 2010 -0400 @@ -315,8 +315,8 @@ The fourth series, $hsf_4$, experimentally recognized to be the most difficult one is recommended by NIST as testing set and is used in our work and some previous work~\cite{Granger+al-2007,Cortes+al-2000,Oliveira+al-2002,Milgram+al-2005} for that purpose. We randomly split the remainder into a training set and a validation set for -model selection. The sizes of these data sets are: for training, XXX for validation, -and XXX for testing. +model selection. The sizes of these data sets are: 651668 for training, 80000 for validation, +and 82587 for testing. The performances reported by previous work on that dataset mostly use only the digits. Here we use all the classes both in the training and testing phase. This is especially useful to estimate the effect of a multi-task setting.