Fri, 16 May 2008 16:38:07 -0400 |
Frederic Bastien |
optimisation of ArrayDataSet
|
Tue, 27 May 2008 13:23:05 -0400 |
James Bergstra |
reinstating changeset 216 clobbered accidentally by 218
|
Fri, 23 May 2008 17:12:12 -0400 |
James Bergstra |
merged
|
Fri, 23 May 2008 17:11:39 -0400 |
James Bergstra |
deprecation note for mlp
|
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
|
Mon, 12 May 2008 17:43:53 -0400 |
Frederic Bastien |
don't assume we have an ArrayDataSet
|
Mon, 12 May 2008 17:40:06 -0400 |
Frederic Bastien |
bugfix, we should advence by the minibatch size.
|
Mon, 12 May 2008 17:37:36 -0400 |
Frederic Bastien |
bugfix in test
|
Mon, 12 May 2008 17:25:52 -0400 |
Frederic Bastien |
bugfix test in case it is not an ArrayDataSet
|
Mon, 12 May 2008 16:52:00 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 16:51:54 -0400 |
Frederic Bastien |
bugfix: make the iterator advance
|
Mon, 12 May 2008 16:24:59 -0400 |
Frederic Bastien |
typo
|
Mon, 12 May 2008 16:22:10 -0400 |
Frederic Bastien |
only exec the test if we are the main
|
Mon, 12 May 2008 16:17:22 -0400 |
James Bergstra |
merged
|
Mon, 12 May 2008 16:16:32 -0400 |
James Bergstra |
new argmax calling convention
|
Mon, 12 May 2008 16:13:48 -0400 |
Frederic Bastien |
merge
|
Mon, 12 May 2008 16:12:29 -0400 |
Frederic Bastien |
optimization
|
Mon, 12 May 2008 16:11:24 -0400 |
Yoshua Bengio |
Fixes in CacheDataSet
|
Mon, 12 May 2008 15:51:43 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 15:51:30 -0400 |
Frederic Bastien |
bugfix
|
Mon, 12 May 2008 15:50:49 -0400 |
Frederic Bastien |
typo
|
Mon, 12 May 2008 15:47:32 -0400 |
Frederic Bastien |
added test for CachedDataSet
|
Mon, 12 May 2008 15:50:34 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 15:50:28 -0400 |
Yoshua Bengio |
Trying to make CacheDataSet work
|
Mon, 12 May 2008 15:35:18 -0400 |
Frederic Bastien |
make some function global to reuse them to test other dataset
|
Mon, 12 May 2008 15:08:18 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 15:08:09 -0400 |
Frederic Bastien |
added missing raise
|
Mon, 12 May 2008 14:15:16 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 14:13:39 -0400 |
Frederic Bastien |
...
|
Mon, 12 May 2008 14:13:19 -0400 |
Frederic Bastien |
bugfix
|
Mon, 12 May 2008 14:11:57 -0400 |
Frederic Bastien |
commented broken test
|
Mon, 12 May 2008 13:54:54 -0400 |
Frederic Bastien |
futur test
|
Wed, 07 May 2008 17:01:51 -0400 |
Frederic Bastien |
added function LookupList.append_lookuplist
|
Wed, 07 May 2008 16:26:28 -0400 |
Frederic Bastien |
typo
|
Mon, 12 May 2008 14:30:21 -0400 |
Yoshua Bengio |
Fixed bugs in dataset to make test_mlp.py work
|
Fri, 09 May 2008 17:38:57 -0400 |
Yoshua Bengio |
Fixes to ApplyFunctionDataSet and other things to make learner and mlp work
|
Fri, 09 May 2008 13:38:54 -0400 |
Yoshua Bengio |
Corrected typos
|
Thu, 08 May 2008 00:54:14 -0400 |
Joseph Turian |
Updated documentation slightly
|
Wed, 07 May 2008 21:40:15 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 21:40:03 -0400 |
Yoshua Bengio |
minor
|
Wed, 07 May 2008 21:22:56 -0400 |
Yoshua Bengio |
Fixed typos in learner.py
|
Wed, 07 May 2008 20:51:24 -0400 |
Yoshua Bengio |
minor edits
|
Wed, 07 May 2008 16:58:06 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 16:57:48 -0400 |
Yoshua Bengio |
minor edits
|
Wed, 07 May 2008 16:22:28 -0400 |
Frederic Bastien |
bugfix
|
Wed, 07 May 2008 16:20:40 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 16:17:25 -0400 |
Frederic Bastien |
bugfix
|
Wed, 07 May 2008 16:17:06 -0400 |
Frederic Bastien |
removed datat that should not be commited
|
Wed, 07 May 2008 16:08:18 -0400 |
Yoshua Bengio |
debugging mlp.py
|
Wed, 07 May 2008 15:46:24 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 15:08:18 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 15:07:56 -0400 |
Yoshua Bengio |
Finished draft of OneHiddenLayerNNetClassifier to debut learner.py
|
Wed, 07 May 2008 15:28:17 -0400 |
James Bergstra |
ported nnet_ops to new theano
|
Wed, 07 May 2008 13:07:33 -0400 |
Frederic Bastien |
added function load_pmat_as_array_dataset and save_array_dataset_as_pmat
|
Wed, 07 May 2008 12:19:36 -0400 |
Frederic Bastien |
removed dependency to plearn
|
Wed, 07 May 2008 12:18:11 -0400 |
Frederic Bastien |
file copied from PLearn/python_modules/plearn/vmat/PMat.py
|
Wed, 07 May 2008 12:12:48 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Wed, 07 May 2008 12:12:43 -0400 |
Frederic Bastien |
...
|
Wed, 07 May 2008 09:16:04 -0400 |
bengioy |
Added another work in progress, for mlp's
|
Tue, 06 May 2008 22:24:55 -0400 |
bengioy |
Worked on OneShotTLearner and implementation of LinearRegression
|
Tue, 06 May 2008 20:01:34 -0400 |
bengioy |
Merged with this morning unsaved edits
|
Tue, 06 May 2008 19:55:29 -0400 |
Yoshua Bengio |
Merges?
|
Tue, 06 May 2008 19:54:43 -0400 |
Yoshua Bengio |
Comments from Pascal V.
|
Tue, 06 May 2008 16:41:45 -0400 |
Frederic Bastien |
added test
|
Tue, 06 May 2008 16:34:48 -0400 |
Frederic Bastien |
bugfix, we keep all the line, but only a some columns
|
Tue, 06 May 2008 16:12:37 -0400 |
Frederic Bastien |
more test
|
Tue, 06 May 2008 16:07:39 -0400 |
Frederic Bastien |
clean up and a few more test
|
Tue, 06 May 2008 16:03:17 -0400 |
Frederic Bastien |
modifed test to accomodate the last change in dataset.py.
|
Tue, 06 May 2008 16:01:53 -0400 |
Frederic Bastien |
by default, in a minibatch without any fixed number of batchs, we need to finish at the end of the dataset. Now we return a minibatch at the end event if this minibacht size != the gived minibatch_size.
|