| Fri, 23 May 2008 17:10:03 -0400 |
James Bergstra |
added LookupList to pylearn namespace
|
| Fri, 23 May 2008 16:01:01 -0400 |
Thierry Bertin-Mahieux |
should have solved the problem with minibatches not handling subsets of fieldnames, although maybe not super efficient
|
| Fri, 23 May 2008 14:16:54 -0400 |
Thierry Bertin-Mahieux |
redo what James had done, so invert node and name
|
| Fri, 23 May 2008 14:07:53 -0400 |
Thierry Bertin-Mahieux |
tester on iterator consistency now triggers a bug in dataset, linked to the combination of minibatch and slicing
|
| Fri, 23 May 2008 13:44:25 -0400 |
Thierry Bertin-Mahieux |
test on simple slicing works
|
| Fri, 23 May 2008 13:16:42 -0400 |
Thierry Bertin-Mahieux |
added a class to test any new dataset
|
| Fri, 23 May 2008 12:22:54 -0400 |
Thierry Bertin-Mahieux |
small debugging
|
| Thu, 22 May 2008 19:08:46 -0400 |
James Bergstra |
harmless typo in ScalarSoftplus.c_code
|
| Thu, 22 May 2008 19:07:51 -0400 |
James Bergstra |
Modified ArrayDataSet's handling of column fields.
|
| Thu, 22 May 2008 17:41:14 -0400 |
James Bergstra |
tlearn->pylearn in mlp
|
| Thu, 22 May 2008 16:31:07 -0400 |
Frederic Bastien |
small modif for test
|
| Wed, 21 May 2008 17:43:56 -0400 |
Thierry Bertin-Mahieux |
previous commit was supposed to concern only one file, dataset.py, try to undo my other changes with this commit (nothing was broken though, just useless debugging prints)
|
| Wed, 21 May 2008 17:42:20 -0400 |
Thierry Bertin-Mahieux |
previous commit was supposed to concern only one file, dataset.py, try to undo my other changes with this commit (nothing was broken though, just useless debugging prints)
|
| Wed, 21 May 2008 17:39:30 -0400 |
Thierry Bertin-Mahieux |
in __get__, problem if the i.stop was None, i being the slice, added one line replacing None by the len(self)
|
| Sat, 17 May 2008 00:01:47 -0400 |
Yoshua Bengio |
work in progress denoising auto-encoder
|
| Sat, 17 May 2008 00:01:26 -0400 |
Yoshua Bengio |
template statscollector
|
| Fri, 16 May 2008 16:39:01 -0400 |
Yoshua Bengio |
back to James' version
|
| Fri, 16 May 2008 16:38:15 -0400 |
Yoshua Bengio |
trying to merge
|
| Fri, 16 May 2008 16:36:27 -0400 |
Yoshua Bengio |
changes made with Pascal but should probably be discarded
|
| Wed, 14 May 2008 14:06:52 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Wed, 14 May 2008 14:06:15 -0400 |
Yoshua Bengio |
debugging mlp.py
|
| Thu, 15 May 2008 15:21:00 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Thu, 15 May 2008 13:10:21 -0400 |
Frederic Bastien |
Added test for ApplyFunctionDataset
|
| Thu, 15 May 2008 13:09:26 -0400 |
Frederic Bastien |
bugfix
|
| Thu, 15 May 2008 13:04:20 -0400 |
Frederic Bastien |
bugfix?
|
| Tue, 13 May 2008 16:42:51 -0400 |
Frederic Bastien |
bugfix
|
| Tue, 13 May 2008 16:02:32 -0400 |
Frederic Bastien |
bugfix
|
| Tue, 13 May 2008 15:29:04 -0400 |
Frederic Bastien |
more explicit comment
|
| Tue, 13 May 2008 15:27:45 -0400 |
Frederic Bastien |
the function should take the example unpacked as an input.
|
| Tue, 13 May 2008 15:12:45 -0400 |
Frederic Bastien |
typo
|
| Tue, 13 May 2008 15:11:24 -0400 |
Frederic Bastien |
small refactoring
|
| Thu, 15 May 2008 12:55:21 -0400 |
Yoshua Bengio |
Complete redesign of learner...
|
| Thu, 15 May 2008 12:46:21 -0400 |
Yoshua Bengio |
Redesign of StatsCollector
|
| Wed, 14 May 2008 20:04:44 -0400 |
James Bergstra |
added early stopping to mlp.__call__
|
| Wed, 14 May 2008 16:24:10 -0400 |
James Bergstra |
progress toward early stopping
|
| Wed, 14 May 2008 14:50:07 -0400 |
James Bergstra |
many changes to NeuralNet
|
| Wed, 14 May 2008 14:49:08 -0400 |
James Bergstra |
added __contains__ to Dataset, added parent constructor call to ArrayDataSet
|
| Wed, 14 May 2008 11:51:08 -0400 |
James Bergstra |
added mlp_factory_approach
|
| Tue, 13 May 2008 20:10:03 -0400 |
James Bergstra |
added ManualNNet
|
| Tue, 13 May 2008 19:37:29 -0400 |
James Bergstra |
support for more int types in crossentropysoftmax1hot
|
| Tue, 13 May 2008 18:39:58 -0400 |
Olivier Breuleux |
added TODO to nnet_ops
|
| Tue, 13 May 2008 18:30:08 -0400 |
Olivier Breuleux |
did some debugging of test_mlp
|
| Tue, 13 May 2008 17:00:53 -0400 |
Yoshua Bengio |
strange bug in linker obtained by 'python test_mlp.py'
|
| Tue, 13 May 2008 15:49:39 -0400 |
Olivier Breuleux |
fixed c_code for the ops in nnet_ops.py
|
| Tue, 13 May 2008 15:35:43 -0400 |
Yoshua Bengio |
mlp seems to work!
|
| Tue, 13 May 2008 15:14:04 -0400 |
James Bergstra |
merged
|
| Tue, 13 May 2008 15:12:20 -0400 |
James Bergstra |
merged
|
| Tue, 13 May 2008 15:11:47 -0400 |
James Bergstra |
s/Output/Input
|
| Tue, 13 May 2008 15:11:39 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Tue, 13 May 2008 15:11:24 -0400 |
Yoshua Bengio |
Added a Print Op
|
| Tue, 13 May 2008 15:04:51 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Tue, 13 May 2008 15:03:16 -0400 |
Frederic Bastien |
more test
|
| Tue, 13 May 2008 14:28:47 -0400 |
Yoshua Bengio |
fixed import of AbstractFunction
|
| Tue, 13 May 2008 13:23:05 -0400 |
Frederic Bastien |
bugfix. Otherwise the example was writed over and not a new one was returned
|
| Tue, 13 May 2008 13:09:59 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Tue, 13 May 2008 13:05:45 -0400 |
Frederic Bastien |
added test for CachedDataSet(ds,cache_all_upon_construction=True)
|
| Tue, 13 May 2008 13:00:54 -0400 |
Frederic Bastien |
more test
|
| Mon, 12 May 2008 18:51:42 -0400 |
Joseph Turian |
Updated documentation
|
| Mon, 12 May 2008 18:40:17 -0400 |
Joseph Turian |
Created exceptions.py
|
| Mon, 12 May 2008 17:51:28 -0400 |
Frederic Bastien |
small refactoring
|
