log

age author description
Thu, 27 Nov 2008 23:27:14 -0500 James Bergstra added WEIRD_STUFF flag to sgd. Relates to theano ticket 238
Thu, 27 Nov 2008 23:16:52 -0500 James Bergstra init rnn.py
Thu, 27 Nov 2008 21:42:02 -0500 James Bergstra moving stuff in algorithms, added rnn
Thu, 20 Nov 2008 12:18:16 -0500 James Bergstra merged
Thu, 20 Nov 2008 12:17:56 -0500 James Bergstra added concept Kalman filter algo to sandbox
Tue, 18 Nov 2008 19:42:12 -0500 desjagui merged
Tue, 18 Nov 2008 19:31:56 -0500 desjagui (James) fixed issues when running locally and rsync command
Mon, 17 Nov 2008 20:05:31 -0500 James Bergstra merged and changed state to dictionary
Mon, 17 Nov 2008 20:03:13 -0500 James Bergstra added SIGINT hanlder to dbdict_run
Mon, 17 Nov 2008 18:38:32 -0500 James Bergstra changes to dbdict to use dict-like instead of object-like state
Thu, 13 Nov 2008 18:40:45 -0500 desjagui Working RBM implementation
Thu, 13 Nov 2008 17:54:56 -0500 James Bergstra m
Thu, 13 Nov 2008 17:01:44 -0500 desjagui first attempt at RBMs in pylearn
Wed, 12 Nov 2008 22:00:20 -0500 James Bergstra added missing files
Wed, 12 Nov 2008 21:57:54 -0500 James Bergstra new file structure layout, factories, etc.
Thu, 20 Nov 2008 06:11:52 -0500 Joseph Turian Moved word preprocessing out
Wed, 19 Nov 2008 18:14:43 -0500 Joseph Turian Added squashfn
Tue, 18 Nov 2008 03:49:37 -0500 Joseph Turian Another bugfix in pylearn.embeddings.length()
Tue, 18 Nov 2008 03:25:54 -0500 Joseph Turian Bugfix in pylearn.embeddings.length()
Tue, 18 Nov 2008 02:57:50 -0500 Joseph Turian Improved embedding word preprocessing.
Tue, 18 Nov 2008 00:32:39 -0500 Joseph Turian Added function length()
Mon, 17 Nov 2008 14:18:28 -0500 Frederic Bastien replaced the use of removed function compile.eval_outputs with theano.function.
Mon, 17 Nov 2008 14:15:19 -0500 Frederic Bastien the function compile.eval_outputs was retired. Now use function instead.
Mon, 17 Nov 2008 13:17:00 -0500 Frederic Bastien bugfix, outputs needed to be in a list in the past, not anymore.
Mon, 17 Nov 2008 13:16:33 -0500 Frederic Bastien bugfix. fix an import bug that I don't understand the cause.
Fri, 14 Nov 2008 16:52:24 -0500 Frederic Bastien corrected import.
Fri, 14 Nov 2008 16:48:17 -0500 Frederic Bastien added one test.
Fri, 14 Nov 2008 16:46:03 -0500 Frederic Bastien better main, allow to debug in a debugger.
Fri, 14 Nov 2008 16:39:59 -0500 Frederic Bastien modified to use the new implecement of ops and use the new interface to theano.function
Fri, 14 Nov 2008 16:38:30 -0500 Frederic Bastien modif source of ops as they where moved.
Fri, 14 Nov 2008 16:37:51 -0500 Frederic Bastien redirect to the good new source.
Fri, 14 Nov 2008 02:09:23 -0500 Joseph Turian merge
Fri, 14 Nov 2008 02:07:20 -0500 Joseph Turian Added theano.Member to Member variables which were passed in during initialization.
Wed, 12 Nov 2008 12:36:09 -0500 James Bergstra init dataset
Wed, 12 Nov 2008 10:54:38 -0500 James Bergstra init
Mon, 03 Nov 2008 00:10:18 -0500 Olivier Breuleux misc
Fri, 31 Oct 2008 16:37:19 -0400 Joseph Turian Small bugfix in hidden weight initialization.
Fri, 31 Oct 2008 11:08:25 -0400 James Bergstra merged
Thu, 30 Oct 2008 19:39:26 -0400 James Bergstra merged
Thu, 30 Oct 2008 19:39:10 -0400 James Bergstra added useless comments
Thu, 30 Oct 2008 23:27:27 -0400 James Bergstra fixed mnist path
Thu, 30 Oct 2008 18:42:16 -0400 Joseph Turian Fixed parameters.
Thu, 30 Oct 2008 11:27:04 -0400 James Bergstra added shapeset1
Wed, 29 Oct 2008 18:23:34 -0400 James Bergstra scrapped ulimit in smallnorb
Wed, 29 Oct 2008 18:06:49 -0400 James Bergstra modifs to smallNorb
Wed, 29 Oct 2008 17:20:18 -0400 James Bergstra removed n_out from smallnorb_iid rval
Wed, 29 Oct 2008 17:09:04 -0400 James Bergstra added smallNorb dataset, switched to PYLEARN_DATA_ROOT
Wed, 29 Oct 2008 11:38:49 -0400 James Bergstra slightly more sophisticated system for finding the mnist data
Wed, 29 Oct 2008 03:29:18 -0400 Joseph Turian Extensions to algorithms, and some cleanup (by defining linear_output result).
Wed, 29 Oct 2008 02:08:56 -0400 Joseph Turian Bug fix
Tue, 28 Oct 2008 13:54:01 -0400 Joseph Turian N-class logistic regression top-layer works
Tue, 28 Oct 2008 13:36:27 -0400 Joseph Turian Added new daa test
Tue, 28 Oct 2008 12:57:49 -0400 James Bergstra removed unpicklable nested classes in logistic regression
Tue, 28 Oct 2008 12:25:15 -0400 Joseph Turian More documentation + todo
Tue, 28 Oct 2008 12:25:04 -0400 Joseph Turian 'x' => 'input'
Tue, 28 Oct 2008 12:09:49 -0400 Joseph Turian A few more ideas, in comments
Tue, 28 Oct 2008 12:09:39 -0400 Joseph Turian nnet_ops => nnet
Tue, 28 Oct 2008 11:40:56 -0400 Joseph Turian merge
Tue, 28 Oct 2008 11:40:31 -0400 Joseph Turian Added test_daa.py
Tue, 28 Oct 2008 11:39:47 -0400 Olivier Breuleux merge