Wed, 15 Jul 2009 13:18:55 -0400 |
Frederic Bastien |
get the mnist data from the pmat file and not the amat file
|
Mon, 13 Jul 2009 16:56:31 -0400 |
Xavier Glorot |
check saturation and noiseseed methods for DAA input groups
|
Fri, 10 Jul 2009 18:14:36 -0400 |
Xavier Glorot |
added a save and load mecanism and fixed bug to DAA_inputs_groups
|
Fri, 10 Jul 2009 16:56:52 -0400 |
Xavier Glorot |
changed behavior of DAAig and StackedDAAig, added a cost scaling parameter
|
Fri, 10 Jul 2009 12:16:20 -0400 |
Frederic Bastien |
fix FillMissing debug mode error. The error was caused by the fact that debug_mode generate an error by default for NaN value. We must disable this check for this op as we deal with NaN value.
|
Fri, 10 Jul 2009 11:31:32 -0400 |
Frederic Bastien |
gix on gcc4.1 FillMissing, seam broken on gcc 4.3
|
Tue, 30 Jun 2009 12:02:11 -0400 |
phamel |
Reverted previous commit
|
Tue, 30 Jun 2009 11:57:20 -0400 |
phamel |
Test commit - Will be reverted
|
Mon, 29 Jun 2009 16:08:00 -0400 |
Frederic Bastien |
dummy change to force the compilation with the good paramter of FillMissing.c_code()
|
Mon, 29 Jun 2009 11:55:29 -0400 |
desjagui |
* fixed test_stacker.py
|
Mon, 29 Jun 2009 09:49:28 -0400 |
Frederic Bastien |
removed manual call to Member and Variable as this is deprecated in theano.
|
Fri, 26 Jun 2009 16:44:55 -0400 |
Olivier Delalleau |
Merged
|
Fri, 26 Jun 2009 09:55:32 -0400 |
Olivier Delalleau |
Fixed test_float
|
Fri, 26 Jun 2009 10:46:45 -0400 |
Frederic Bastien |
implemented FillMissing.c_code. It use the new c_no_compile_args to remove -ffast-math and -ffinite-math-only as they broke isnan.
|
Wed, 24 Jun 2009 10:53:55 -0400 |
Olivier Delalleau |
Fixed some SGD tests
|
Sun, 21 Jun 2009 20:16:23 -0400 |
Xavier Glorot |
Sigmoid before logistic regression to avoid small gradient with tanh in StackedDAAig
|
Sat, 13 Jun 2009 22:02:13 -0400 |
Foo Bar |
Merge
|
Sat, 13 Jun 2009 10:11:43 -0400 |
Xavier Glorot |
change seed initialisation for random object and weigth init for logistic regression
|
Thu, 11 Jun 2009 15:44:32 -0400 |
Frederic Bastien |
small optimisation
|
Thu, 11 Jun 2009 13:35:31 -0400 |
Frederic Bastien |
test more case in FillMissing and print the time of the op.
|
Thu, 11 Jun 2009 11:37:24 -0400 |
Xavier Glorot |
fix a bug for the weight decay
|
Wed, 10 Jun 2009 13:45:52 -0400 |
Frederic Bastien |
remove something that should not have been commited.
|
Wed, 10 Jun 2009 13:43:27 -0400 |
Frederic Bastien |
added more test for the FillMissing op.
|
Wed, 10 Jun 2009 13:42:56 -0400 |
Frederic Bastien |
opt of the FillMissing op. Now 80-90% faster python implementation.
|
Tue, 09 Jun 2009 21:39:50 -0400 |
Frederic Bastien |
scall optimisation to FillMissing.
|
Tue, 09 Jun 2009 21:37:58 -0400 |
Frederic Bastien |
added test for FillMissing op.
|
Mon, 08 Jun 2009 13:14:09 -0400 |
Xavier Glorot |
small change to Checks of scan_inputs_groups ops
|
Mon, 08 Jun 2009 12:14:14 -0400 |
Frederic Bastien |
very small opt.
|
Fri, 05 Jun 2009 15:27:21 -0400 |
Xavier Glorot |
Better declaration of totallocal_update method in StackedDAAig
|
Fri, 05 Jun 2009 15:11:53 -0400 |
Xavier Glorot |
added a totallocal_update method to StackedDAAig
|
Wed, 03 Jun 2009 14:25:56 -0400 |
Xavier Glorot |
Normalized tanh to be equivalent to sigmoid in DAAig
|
Wed, 03 Jun 2009 13:54:31 -0400 |
Frederic Bastien |
fix typo in comment.
|
Wed, 03 Jun 2009 04:07:30 -0400 |
desjagui |
BUG FIXES !!!!!!!
|
Tue, 02 Jun 2009 22:29:49 -0400 |
Pascal Lamblin |
merge
|
Tue, 02 Jun 2009 22:29:21 -0400 |
Pascal Lamblin |
Finalize new validation split: indices are now randomized again inside
|
Tue, 02 Jun 2009 22:26:29 -0400 |
Olivier Delalleau |
Merged
|
Tue, 02 Jun 2009 22:26:04 -0400 |
Olivier Delalleau |
Fix to the 'by_pair' corruption pattern
|
Tue, 02 Jun 2009 14:40:43 -0400 |
Olivier Delalleau |
Fixed bug introduced in previous change meant to improve numerical stability
|
Tue, 02 Jun 2009 21:15:41 -0400 |
Pascal Lamblin |
merge
|
Tue, 02 Jun 2009 21:15:21 -0400 |
Pascal Lamblin |
Prepare the way for the new train/valid split, based on object instances.
|
Tue, 02 Jun 2009 20:21:35 -0400 |
James Bergstra |
merge
|
Tue, 02 Jun 2009 20:21:21 -0400 |
James Bergstra |
better numeric stability in tile_image
|
Tue, 02 Jun 2009 20:20:48 -0400 |
James Bergstra |
fixed typos in wrap_libsvm
|
Tue, 02 Jun 2009 20:20:03 -0400 |
James Bergstra |
added methods kwarg to sgd module
|
Tue, 02 Jun 2009 20:19:30 -0400 |
James Bergstra |
added doc
|
Tue, 02 Jun 2009 13:51:22 -0400 |
Olivier Delalleau |
Merged
|
Tue, 02 Jun 2009 13:50:43 -0400 |
Olivier Delalleau |
New option 'corruption_pattern' to alter the way inputs are corrupted
|
Tue, 02 Jun 2009 11:38:23 -0400 |
Xavier Glorot |
fixed numerical instability for cross entropy cost calculation of DAAig
|
Tue, 02 Jun 2009 11:31:50 -0400 |
Olivier Delalleau |
Added option to allow one to try and reconstruct originally missing inputs
|
Tue, 02 Jun 2009 10:14:00 -0400 |
Olivier Delalleau |
FillMissing can now impute missing values by an array instead of a single constant
|
Mon, 01 Jun 2009 17:44:56 -0400 |
bergstra |
typos in parameter names
|
Mon, 01 Jun 2009 00:22:35 -0400 |
bergstra |
added hard_time_limit to stopper
|
Sun, 31 May 2009 05:07:55 -0400 |
desjagui |
With float64 and normalize=True, dataset doesn't even fit in memory.
|
Fri, 29 May 2009 10:48:20 -0400 |
Xavier Glorot |
fix a bad declaration of the updates in StackedDAAig
|
Thu, 28 May 2009 12:12:34 -0400 |
Xavier Glorot |
changed name to NLL method to the StackedDAAig
|
Thu, 28 May 2009 12:06:33 -0400 |
Xavier Glorot |
added a NLL method to the StackedDAAig
|
Wed, 27 May 2009 23:15:00 -0400 |
desjagui |
added comments to norb_small
|
Wed, 27 May 2009 21:28:25 -0400 |
desjagui |
Official version of smallNORB, with stereo images of size 96x96
|
Wed, 27 May 2009 15:25:56 -0400 |
Olivier Delalleau |
Fixed the SGD tests
|
Wed, 27 May 2009 14:46:01 -0400 |
Olivier Delalleau |
Fixed some imports, but test_stacker is still not working
|
Wed, 27 May 2009 14:15:35 -0400 |
Olivier Delalleau |
Fixed imports so that more tests pass
|
Wed, 27 May 2009 13:57:10 -0400 |
Olivier Delalleau |
Test test_tzanetakis now passes
|
Wed, 27 May 2009 13:54:13 -0400 |
Olivier Delalleau |
Fixed some imports
|
Wed, 27 May 2009 13:53:50 -0400 |
Olivier Delalleau |
Fixed import so that make_test_datasets can be imported without crashing
|
Wed, 27 May 2009 13:26:33 -0400 |
Olivier Delalleau |
Simplified code now that it is not a unittest anymore
|
Wed, 27 May 2009 13:25:20 -0400 |
Olivier Delalleau |
Renamed test_speed.py into check_speed.py so that nosetests does not run it
|
Wed, 27 May 2009 12:08:18 -0400 |
Olivier Delalleau |
Made test_speed faster when run by nosetests
|
Wed, 27 May 2009 11:48:05 -0400 |
Olivier Delalleau |
Fixed test_speed test
|
Wed, 27 May 2009 11:46:08 -0400 |
Olivier Delalleau |
Added empty __init__.py so that old_dataset can be seen as a module
|
Wed, 27 May 2009 09:59:39 -0400 |
Olivier Delalleau |
Merged
|
Wed, 27 May 2009 09:59:25 -0400 |
Olivier Delalleau |
Replaced debug special code for missing values (-123456) by truly missing (NaN)
|
Tue, 26 May 2009 18:45:09 -0400 |
desjagui |
* when creating the sgd minimizer, the user can ask that step_cost compute other
|
Tue, 26 May 2009 17:39:43 -0400 |
Joseph Turian |
Added more descriptive comments to crossentropy and KL divergence.
|
Mon, 25 May 2009 23:13:56 -0400 |
Olivier Delalleau |
Fixes to the handling of missing values in input
|
Mon, 25 May 2009 23:11:38 -0400 |
Olivier Delalleau |
Some fixes to FillMissing, and added MaskGradient (another Op to move elsewhere later)
|
Mon, 25 May 2009 11:45:37 -0400 |
Olivier Delalleau |
Merged
|
Mon, 25 May 2009 11:43:50 -0400 |
Olivier Delalleau |
Added new option 'ignore_missing' to deal with missing values in input
|
Mon, 25 May 2009 11:42:25 -0400 |
Olivier Delalleau |
New class MaskSelect (should probably be moved to another file)
|
Mon, 25 May 2009 10:23:00 -0400 |
Olivier Delalleau |
New class FillMissing (should probably be moved to another file later)
|
Sun, 24 May 2009 17:16:38 -0400 |
Pascal Lamblin |
Bugfix and improvement to NIPS09Stopper
|
Fri, 22 May 2009 15:14:34 -0400 |
Xavier Glorot |
improved readability DAA_inputs_groups and scan_inputs_groups
|
Fri, 22 May 2009 14:13:38 -0400 |
Olivier Delalleau |
Replaced tabs by 4 blank spaces
|
Fri, 22 May 2009 14:12:17 -0400 |
Olivier Delalleau |
Added a safety assert, just in case
|
Fri, 22 May 2009 14:11:51 -0400 |
Olivier Delalleau |
Fixed minor typo in comment
|
Fri, 22 May 2009 13:43:23 -0400 |
Olivier Delalleau |
Cosmetic changes
|
Fri, 22 May 2009 10:04:04 -0400 |
Olivier Delalleau |
Renamed Alloc into alloc
|
Fri, 22 May 2009 10:03:29 -0400 |
Olivier Delalleau |
Merged
|
Fri, 22 May 2009 10:03:10 -0400 |
Olivier Delalleau |
Renamed Alloc into alloc
|
Thu, 21 May 2009 19:52:46 -0400 |
Xavier Glorot |
improved initialization of StackedDAAig
|
Thu, 21 May 2009 14:11:54 -0400 |
Xavier Glorot |
comments DAA_inputs_groups
|
Thu, 21 May 2009 12:54:41 -0400 |
Xavier Glorot |
better definition of parameters for DAAig
|
Thu, 21 May 2009 12:18:36 -0400 |
Xavier Glorot |
added a parameter to SatckedDAAig
|
Wed, 20 May 2009 13:40:10 -0400 |
Xavier Glorot |
added a DAAig module and a StackedDAAig module to deal with auxiliary output possibly missing in algorithm.sandbox
|
Tue, 19 May 2009 19:00:34 -0400 |
Xavier Glorot |
fixed bug of scan_inputs_groups
|
Tue, 19 May 2009 11:23:54 -0400 |
Xavier Glorot |
improved efficiency of scan_inputs_groups
|
Fri, 15 May 2009 17:52:24 -0400 |
Pascal Lamblin |
Add another kind of early stopper for NIPS 09
|
Fri, 15 May 2009 17:51:33 -0400 |
Pascal Lamblin |
Oops, reverting
|
Fri, 15 May 2009 17:47:53 -0400 |
Pascal Lamblin |
Add another kind of early stopper
|
Thu, 14 May 2009 20:01:04 -0400 |
James Bergstra |
merge
|
Thu, 14 May 2009 20:00:39 -0400 |
James Bergstra |
added datasets/imagenet
|
Thu, 14 May 2009 19:34:21 -0400 |
Xavier Glorot |
added a Mask creation Op and fixed some bugs
|
Thu, 14 May 2009 18:25:10 -0400 |
James Bergstra |
added filetensor.arraylike
|
Thu, 14 May 2009 17:00:22 -0400 |
James Bergstra |
merge
|
Thu, 14 May 2009 17:00:10 -0400 |
James Bergstra |
added DynamicNormalizer to exponential_mean
|
Thu, 14 May 2009 16:59:20 -0400 |
James Bergstra |
additions to datasets/tagatune
|
Thu, 14 May 2009 16:58:14 -0400 |
James Bergstra |
do not read data file on import
|
Thu, 14 May 2009 16:54:59 -0400 |
James Bergstra |
added picklable svm_model to wrap_libsvm
|
Thu, 14 May 2009 16:33:38 -0400 |
James Bergstra |
added io/audio that can read mp3s
|
Tue, 12 May 2009 15:34:38 -0400 |
Foo Bar |
add direclty the file scan_inputs_groups.py to sandbox and remove the directory input_groups
|
Tue, 12 May 2009 14:51:25 -0400 |
Xavier Glorot |
Remplaced the name of the scan_input_groups directory and files
|
Tue, 12 May 2009 14:35:29 -0400 |
Foo Bar |
adding Op to deal with static missing inputs groups efficiently in the dense DAA framework
|
Mon, 20 Apr 2009 16:53:03 -0400 |
James Bergstra |
adding tagatune
|
Mon, 20 Apr 2009 16:52:55 -0400 |
James Bergstra |
added option for custom path in tzanetakis
|
Wed, 08 Apr 2009 19:53:18 -0400 |
James Bergstra |
better scan
|
Tue, 07 Apr 2009 18:00:24 -0400 |
James Bergstra |
added README for lib
|
Tue, 07 Apr 2009 17:56:58 -0400 |
James Bergstra |
adding scan1 op
|
Thu, 02 Apr 2009 17:57:51 -0400 |
James Bergstra |
small correction to exponential_mean
|
Thu, 02 Apr 2009 15:08:42 -0400 |
James Bergstra |
added exponential_mean
|
Thu, 02 Apr 2009 15:08:22 -0400 |
James Bergstra |
added updates parameter to sgd
|
Wed, 01 Apr 2009 19:48:47 -0400 |
James Bergstra |
merge
|
Wed, 01 Apr 2009 19:48:32 -0400 |
James Bergstra |
changes to tzanetakis and wavread
|
Mon, 30 Mar 2009 20:48:04 -0400 |
Joseph Turian |
merge
|
Thu, 20 Nov 2008 06:38:06 -0500 |
Joseph Turian |
Added preprocessing back in
|
Mon, 30 Mar 2009 19:51:13 -0400 |
James Bergstra |
adding wavread and tzanetakis dataset
|
Mon, 30 Mar 2009 16:15:24 -0400 |
James Bergstra |
removed Member calls from logistic regression
|
Mon, 30 Mar 2009 16:00:29 -0400 |
James Bergstra |
moved test_filetensor to tests subdir
|
Mon, 30 Mar 2009 15:44:42 -0400 |
James Bergstra |
added sgd_minimizer back into sgd
|
Mon, 30 Mar 2009 12:26:01 -0400 |
James Bergstra |
merge
|
Mon, 30 Mar 2009 12:25:42 -0400 |
James Bergstra |
updating minimizer, sgd to new theano. added sgd tests
|
Wed, 11 Mar 2009 11:13:29 -0400 |
desjagui |
Changed RModule to deprecated.RModule .... temporarily until they are fixed with
|
Wed, 11 Mar 2009 00:09:22 -0400 |
Joseph Turian |
Trying to fix gradient in logfactorial
|
Tue, 10 Mar 2009 20:58:16 -0400 |
Joseph Turian |
Updated comments in nlpoisson cost
|
Tue, 10 Mar 2009 19:03:38 -0400 |
Joseph Turian |
Refactored poisson loss.
|
Tue, 10 Mar 2009 15:58:52 -0400 |
Joseph Turian |
Added a gradient test for nlpoisson.
|
Mon, 09 Mar 2009 03:11:20 -0400 |
Joseph Turian |
Added preliminary code for computing negative log Poisson cost
|
Mon, 09 Mar 2009 00:25:46 -0400 |
Joseph Turian |
Added a cost to sandbox, building out Poisson regressor
|
Tue, 03 Mar 2009 11:37:56 -0500 |
Frederic Bastien |
added pylearn.datasets.MNIST.first_10 and pylearn.datasets.MNIST.first_100. They are usefull to test with small dataset.
|
Fri, 20 Feb 2009 15:08:46 -0500 |
Pascal Lamblin |
merge
|
Fri, 20 Feb 2009 15:08:29 -0500 |
Pascal Lamblin |
Get rid of old dbdict
|
Fri, 13 Feb 2009 13:22:26 -0500 |
Frederic Bastien |
if PYLEARN_DATA_ROOT don't exist try DBPATH.
|
Wed, 11 Feb 2009 01:43:14 -0500 |
bergstra |
merge
|
Wed, 11 Feb 2009 01:42:58 -0500 |
bergstra |
print warning on undefined PYLEARN_DATA_ROOT
|
Wed, 11 Feb 2009 01:42:26 -0500 |
bergstra |
added image_tiling
|
Wed, 04 Feb 2009 20:02:05 -0500 |
James Bergstra |
revised classification and LogReg_New
|
Wed, 04 Feb 2009 18:04:05 -0500 |
James Bergstra |
factoring out classification from LogReg_New
|
Wed, 04 Feb 2009 15:56:20 -0500 |
James Bergstra |
merge
|
Wed, 04 Feb 2009 15:56:00 -0500 |
James Bergstra |
adding a little hacky script to flickr that renders a few images as png
|
Wed, 04 Feb 2009 15:55:19 -0500 |
James Bergstra |
added new way of writing logistic regression
|
Tue, 03 Feb 2009 16:47:40 -0500 |
Pascal Lamblin |
Get rid of dbdict, it now has its own repository.
|
Mon, 02 Feb 2009 17:41:54 -0500 |
desjagui |
Changed database schema to be more efficient:
|
Fri, 30 Jan 2009 16:54:06 -0500 |
Joseph Turian |
Added tag sequencelabelling 20090130-rerun for changeset 5f9ffefa9ca8
|
Fri, 30 Jan 2009 16:38:46 -0500 |
Joseph Turian |
pylearn/algorithms/logistic_regression.py:
sequencelabelling 20090130-rerun
|
Fri, 30 Jan 2009 16:38:02 -0500 |
Joseph Turian |
Bugfix in cost.py to correctly use theano.tensor.xlogx
|
Sat, 24 Jan 2009 17:25:41 -0500 |
James Bergstra |
merge
|
Sat, 24 Jan 2009 17:24:55 -0500 |
James Bergstra |
revised tzanetakis, added data centering
|
Thu, 22 Jan 2009 21:14:03 -0500 |
Pascal Lamblin |
Add "FUCKED_UP" (666) status.
|
Wed, 21 Jan 2009 18:53:35 -0500 |
desjagui |
Updated sql commands for creating the view
|
Wed, 21 Jan 2009 16:02:07 -0500 |
James Bergstra |
merge
|
Wed, 21 Jan 2009 16:01:16 -0500 |
James Bergstra |
changed insert_ methods in sql to not clobber internal keys STATUS, PRIORITY, HASH
|
Wed, 21 Jan 2009 03:37:58 -0500 |
projects |
Reverting out of changeset 633,634. Hopefully i did this write !
|
Wed, 21 Jan 2009 03:27:13 -0500 |
desjagui |
merge
|
Wed, 21 Jan 2009 03:23:50 -0500 |
desjagui |
merged
|
Wed, 21 Jan 2009 03:20:16 -0500 |
desjagui |
Cost should be summed over the units, but averaged across batches.
|
Tue, 20 Jan 2009 23:32:24 -0500 |
James Bergstra |
added priority keyword arg to sql.insert_job and insert_dict
|
Tue, 20 Jan 2009 23:30:17 -0500 |
James Bergstra |
added priority-based dequeuing to sql.book_dct_postgres
|
Mon, 19 Jan 2009 18:35:43 -0500 |
James Bergstra |
merge
|
Mon, 19 Jan 2009 18:34:13 -0500 |
James Bergstra |
added get by id to api0
|
Mon, 19 Jan 2009 18:10:48 -0500 |
James Bergstra |
moving away from mnist_factory
|
Mon, 19 Jan 2009 00:58:06 -0500 |
desjagui |
remove debug prints
|
Mon, 19 Jan 2009 00:46:28 -0500 |
desjagui |
Added hash value for each dict in Trial table.
|
Sun, 18 Jan 2009 22:17:56 -0500 |
James Bergstra |
fixing session management in db dict update
|
Sun, 18 Jan 2009 22:00:16 -0500 |
James Bergstra |
looping works, eagerload of booked jobs works by str() HACK
|
Sun, 18 Jan 2009 21:39:28 -0500 |
James Bergstra |
api0 and sql seem to work with session closing
|
Sun, 18 Jan 2009 21:14:14 -0500 |
James Bergstra |
untested changes to close sessions in api0
|
Sat, 17 Jan 2009 21:23:36 -0500 |
James Bergstra |
changed sql to use filter_eq_dct
|
Sat, 17 Jan 2009 21:20:32 -0500 |
James Bergstra |
added api0.filter_eq_dct
|
Sat, 17 Jan 2009 19:13:17 -0500 |
lamblinp |
Fix typo
|
Sat, 17 Jan 2009 19:06:21 -0500 |
lamblinp |
More complete version of shapeset1 dataset.
|
Sat, 17 Jan 2009 17:38:17 -0500 |
James Bergstra |
merge
|
Sat, 17 Jan 2009 17:37:55 -0500 |
James Bergstra |
updated query to support new dot syntax, and hacked api0 to mirror dbdict.status and dbdict.priority to true columns
|
Sat, 17 Jan 2009 00:34:14 -0500 |
Pascal Lamblin |
Use usual data_root
|
Fri, 16 Jan 2009 19:10:50 -0500 |
lamblinp |
merge.
|
Fri, 16 Jan 2009 19:10:09 -0500 |
lamblinp |
- Account for exception name change in sqlalchemy 0.5.0
|
Fri, 16 Jan 2009 16:27:44 -0500 |
Olivier Breuleux |
removed an obtrusive try/except
|
Fri, 16 Jan 2009 15:53:47 -0500 |
Olivier Breuleux |
merge
|
Fri, 16 Jan 2009 15:53:22 -0500 |
Olivier Breuleux |
added -f flag to sqlschedule and sqlschedule_filemerge
|
Thu, 15 Jan 2009 22:23:43 -0500 |
James Bergstra |
merged
|
Thu, 15 Jan 2009 22:22:45 -0500 |
James Bergstra |
added dbdict-run cmdline option (-2 --allow_sigint) to allow ctrl-c to interrupt progrma
|
Thu, 15 Jan 2009 22:21:35 -0500 |
James Bergstra |
added comments to amat
|
Thu, 15 Jan 2009 22:21:04 -0500 |
James Bergstra |
initial tzanetakis dataset
|
Thu, 15 Jan 2009 17:12:36 -0500 |
Olivier Breuleux |
merge
|
Thu, 15 Jan 2009 17:07:49 -0500 |
Olivier Breuleux |
added sqlschedule_filemerge to newstuff
|
Wed, 14 Jan 2009 17:22:23 -0500 |
James Bergstra |
fixed flickr relpath mistake
|
Wed, 14 Jan 2009 17:00:57 -0500 |
James Bergstra |
updated flickr to row-major files
|
Wed, 14 Jan 2009 15:54:39 -0500 |
James Bergstra |
initial flickr
|
Tue, 13 Jan 2009 20:08:06 -0500 |
James Bergstra |
misc small changes
|
Tue, 13 Jan 2009 16:00:36 -0500 |
james |
merged
|
Tue, 13 Jan 2009 16:00:24 -0500 |
james |
revised newstuff.resolve to do more importing
|
Mon, 12 Jan 2009 18:47:10 -0500 |
Olivier Breuleux |
merge
|
Mon, 12 Jan 2009 18:46:46 -0500 |
Olivier Breuleux |
corrected filemerge
|
Thu, 18 Dec 2008 20:10:35 -0500 |
Olivier Breuleux |
fixed small bug with filemerge
|
Thu, 18 Dec 2008 18:09:23 -0500 |
Olivier Breuleux |
added --dry-run (-n) option to cmdline, added filemerge
|
Thu, 08 Jan 2009 15:11:54 -0500 |
Olivier Delalleau |
Minor cosmetic changes
|
Fri, 19 Dec 2008 16:46:51 -0500 |
Joseph Turian |
Two minor fixes.
|
Wed, 17 Dec 2008 18:16:30 -0500 |
Olivier Breuleux |
fixed the behavior when raising errors and redirecting stderr
|
Wed, 17 Dec 2008 15:39:30 -0500 |
James Bergstra |
dbdict stuff
|
Wed, 17 Dec 2008 15:38:37 -0500 |
James Bergstra |
using newstuff
|
Tue, 16 Dec 2008 10:09:53 -0500 |
Frederic Bastien |
made the file executable.
|
Fri, 05 Dec 2008 22:42:40 -0500 |
Olivier Breuleux |
fixed broken help
|
Fri, 05 Dec 2008 17:05:20 -0500 |
Olivier Breuleux |
merge
|
Fri, 05 Dec 2008 17:05:06 -0500 |
Olivier Breuleux |
added command line options
|
Fri, 05 Dec 2008 15:58:43 -0500 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn_refactor
|
Fri, 05 Dec 2008 15:58:40 -0500 |
Frederic Bastien |
fix import
|
Fri, 05 Dec 2008 15:56:42 -0500 |
Frederic Bastien |
removed some code that is not needed anymore as the bug is fixed. I will add a test in module later.
|
Fri, 05 Dec 2008 15:38:04 -0500 |
Frederic Bastien |
added one test.
|
Thu, 04 Dec 2008 17:07:29 -0500 |
Olivier Breuleux |
doc fix
|
Thu, 04 Dec 2008 16:53:03 -0500 |
Olivier Breuleux |
removed crud
|
Thu, 04 Dec 2008 16:51:58 -0500 |
Olivier Breuleux |
merge
|
Thu, 04 Dec 2008 16:51:46 -0500 |
Olivier Breuleux |
bugfixes and a lot of documentation
|
Thu, 04 Dec 2008 11:03:38 -0500 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn_refactor
|
Thu, 04 Dec 2008 10:56:44 -0500 |
Frederic Bastien |
added test for a bug that James reported to me.
|
Thu, 04 Dec 2008 10:56:13 -0500 |
Frederic Bastien |
fix import.
|
Wed, 03 Dec 2008 23:23:03 -0500 |
Olivier Breuleux |
added host name and workdir to the db
|
Wed, 03 Dec 2008 22:29:40 -0500 |
Olivier Breuleux |
removed references to file locking packages
|
Wed, 03 Dec 2008 22:28:25 -0500 |
Olivier Breuleux |
merge
|
Wed, 03 Dec 2008 22:28:17 -0500 |
Olivier Breuleux |
small fix to test_aa
|
Wed, 03 Dec 2008 22:26:31 -0500 |
Olivier Breuleux |
improvements to dbdict interface
|
Wed, 03 Dec 2008 18:52:34 -0500 |
Olivier Breuleux |
another checkpoint
|
Wed, 03 Dec 2008 16:07:04 -0500 |
Olivier Breuleux |
checkpoint
|
Sat, 29 Nov 2008 16:48:49 -0500 |
Olivier Breuleux |
new stuff
|
Wed, 03 Dec 2008 17:24:37 -0500 |
desjagui |
merge
|
Wed, 03 Dec 2008 17:21:05 -0500 |
desjagui |
* added NStages as a stopper (moved from hpu/conv)
|
Wed, 03 Dec 2008 17:15:20 -0500 |
James Bergstra |
removed squashfn.py: better served by factory or dynamic symbol loading
|
Wed, 03 Dec 2008 17:14:18 -0500 |
James Bergstra |
merged from pylearn_trunk
|
Mon, 01 Dec 2008 16:16:21 -0500 |
Frederic Bastien |
put the new test in a different test fct.
|
Mon, 01 Dec 2008 16:15:10 -0500 |
Frederic Bastien |
added a test for the WEIRD_STUFF flag in theano ticket 239
|
Mon, 01 Dec 2008 16:14:14 -0500 |
Frederic Bastien |
removed print
|
Mon, 01 Dec 2008 16:12:47 -0500 |
Frederic Bastien |
pass the WEIRD_STUFF flag as init argument to allow the creation of a test.
|
Mon, 01 Dec 2008 15:50:50 -0500 |
Frederic Bastien |
fixed import
|
Mon, 01 Dec 2008 15:49:16 -0500 |
Frederic Bastien |
fixed some import.
|
Mon, 01 Dec 2008 15:37:43 -0500 |
Frederic Bastien |
fixed import
|
Mon, 01 Dec 2008 15:36:19 -0500 |
Frederic Bastien |
fixed one import
|
Mon, 01 Dec 2008 15:34:25 -0500 |
Frederic Bastien |
fixed import.
|
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
|
Tue, 28 Oct 2008 11:39:27 -0400 |
Olivier Breuleux |
made logistic_regression classes compatible with stacker
|
Tue, 28 Oct 2008 10:54:26 -0400 |
Joseph Turian |
Moved weights.py out of sandbox
|
Tue, 28 Oct 2008 03:31:36 -0400 |
Joseph Turian |
Another bit of documentation
|
Tue, 28 Oct 2008 02:39:00 -0400 |
Joseph Turian |
Added another todo
|
Tue, 28 Oct 2008 02:21:50 -0400 |
Joseph Turian |
DAA code more generic:
|
Tue, 28 Oct 2008 02:02:17 -0400 |
Joseph Turian |
Small change to error message
|
Tue, 28 Oct 2008 01:37:32 -0400 |
Joseph Turian |
Small bugfix in regularization
|
Tue, 28 Oct 2008 01:33:27 -0400 |
Joseph Turian |
Added Yoshua's explanation
|
Tue, 28 Oct 2008 00:23:53 -0400 |
Olivier Breuleux |
merge
|
Tue, 28 Oct 2008 00:23:13 -0400 |
Olivier Breuleux |
bugfix
|
Mon, 27 Oct 2008 19:40:17 -0400 |
James Bergstra |
added import to make test_aa run
|
Mon, 27 Oct 2008 17:29:03 -0400 |
James Bergstra |
merged
|
Mon, 27 Oct 2008 17:28:48 -0400 |
James Bergstra |
typo
|
Fri, 24 Oct 2008 13:28:30 -0400 |
James Bergstra |
stopper.find_min returns tuple instead of just best
|
Fri, 24 Oct 2008 13:28:00 -0400 |
James Bergstra |
added sgd
|
Mon, 27 Oct 2008 17:26:00 -0400 |
Olivier Breuleux |
added a few algorithms
|
Thu, 23 Oct 2008 18:06:21 -0400 |
James Bergstra |
typo in MNIST.train_valid_test
|
Thu, 23 Oct 2008 18:05:46 -0400 |
James Bergstra |
added Stopper.find_min
|
Thu, 23 Oct 2008 18:05:09 -0400 |
James Bergstra |
__instance_type__ -> InstanceType
|
Thu, 23 Oct 2008 13:26:42 -0400 |
James Bergstra |
changed weight initialization for logistic regression
|
Thu, 23 Oct 2008 13:26:11 -0400 |
James Bergstra |
added train_valid_test
|
Wed, 22 Oct 2008 15:56:53 -0400 |
James Bergstra |
new stuff: algorithms/logistic_regression, datasets/MNIST
|
Tue, 21 Oct 2008 16:32:06 -0400 |
Joseph Turian |
Split into preprocess for words and sequences
|
Tue, 21 Oct 2008 16:24:44 -0400 |
Joseph Turian |
Moved embeddings out of sandbox
|
Mon, 20 Oct 2008 19:14:06 -0400 |
Joseph Turian |
Fixed a bug in how embeddings are read
|
Wed, 15 Oct 2008 18:59:55 -0400 |
Joseph Turian |
Added pylearn.sandbox.weights.random_weights
|
Wed, 15 Oct 2008 17:00:35 -0400 |
Joseph Turian |
merge
|
Wed, 15 Oct 2008 17:00:26 -0400 |
Joseph Turian |
More debug output
|
Wed, 08 Oct 2008 17:31:26 -0400 |
Joseph Turian |
Updated file locations
|
Fri, 10 Oct 2008 10:43:43 -0400 |
Olivier Delalleau |
Removed import of nnet_ops since it is now deprecated
|
Wed, 08 Oct 2008 01:09:23 -0400 |
Joseph Turian |
Rearranged
|
Tue, 07 Oct 2008 23:07:23 -0400 |
Joseph Turian |
\/ -> /
|
Tue, 07 Oct 2008 23:00:10 -0400 |
Joseph Turian |
Fixed embedding preprocessing
|
Tue, 07 Oct 2008 19:13:53 -0400 |
Joseph Turian |
Polished embeddings module
|
Tue, 07 Oct 2008 18:21:32 -0400 |
Joseph Turian |
Deprecated pylearn.nnet_ops.
|
Tue, 07 Oct 2008 17:56:52 -0400 |
Joseph Turian |
Added sandbox.embeddings
|
Thu, 02 Oct 2008 13:46:13 -0400 |
delallea |
Reverted change ce6b4fd3ab29 (I do not believe anymore it was a typo)
|
Thu, 02 Oct 2008 13:41:43 -0400 |
delallea |
Merged
|
Thu, 04 Sep 2008 13:48:47 -0400 |
delallea |
Fixed typo in help
|
Mon, 29 Sep 2008 16:04:51 -0400 |
delallea |
Typo fix in help
|
Thu, 04 Sep 2008 14:46:30 -0400 |
Joseph Turian |
Added a KL-divergence.
|
Thu, 04 Sep 2008 14:46:17 -0400 |
Joseph Turian |
Added an XlogX op.
|
Wed, 03 Sep 2008 17:14:49 -0400 |
Joseph Turian |
updated doc
|
Wed, 03 Sep 2008 17:08:54 -0400 |
Joseph Turian |
Added some documentation
|
Wed, 27 Aug 2008 17:08:33 -0400 |
James Bergstra |
fixed c typos, math error in nnet_ops.py
|
Mon, 25 Aug 2008 18:15:43 -0400 |
Pascal Lamblin |
Add argmax as output of the big softmax-NLL thingy.
|
Fri, 22 Aug 2008 17:34:06 -0400 |
Pascal Lamblin |
Ignore .swp and core files.
|
Fri, 22 Aug 2008 17:33:19 -0400 |
Pascal Lamblin |
New tests for softmax.
|
Fri, 22 Aug 2008 17:33:06 -0400 |
Pascal Lamblin |
Hopefully last bugfix in Softmax
|
Fri, 22 Aug 2008 15:53:34 -0400 |
Pascal Lamblin |
Finished derivative of softmax gradient.
|
Thu, 21 Aug 2008 13:55:43 -0400 |
Pascal Lamblin |
merge
|
Thu, 21 Aug 2008 13:55:16 -0400 |
Pascal Lamblin |
Work on softmax operators
|
Tue, 19 Aug 2008 18:41:39 -0400 |
Joseph Turian |
More doc
|
Thu, 14 Aug 2008 11:44:07 -0400 |
Olivier Delalleau |
Minor typo fixes
|
Wed, 06 Aug 2008 19:39:36 -0400 |
Olivier Breuleux |
added two methods to make_test_datasets
|
Wed, 06 Aug 2008 19:39:14 -0400 |
Olivier Breuleux |
image_tools
|
Mon, 04 Aug 2008 16:29:30 -0400 |
Olivier Breuleux |
merge
|
Mon, 04 Aug 2008 16:21:59 -0400 |
Olivier Breuleux |
log2->log in cost
|
Thu, 31 Jul 2008 17:25:35 -0400 |
Pascal Lamblin |
Example showing parameter updates.
|
Tue, 29 Jul 2008 11:16:05 -0400 |
Yoshua Bengio |
added a test for LinearRegression
|
Tue, 29 Jul 2008 10:19:25 -0400 |
Yoshua Bengio |
Adding file make_test_datasets to host simple data-generating processes
|
Tue, 29 Jul 2008 09:36:09 -0400 |
Yoshua Bengio |
merge
|
Fri, 25 Jul 2008 17:02:28 -0400 |
Thierry Bertin-Mahieux |
simple example of theano
|
Fri, 25 Jul 2008 16:59:57 -0400 |
Thierry Bertin-Mahieux |
simple example of theano
|
Tue, 22 Jul 2008 16:44:42 -0400 |
Yoshua Bengio |
Showing the path to an online version of linear regressor.
|
Tue, 22 Jul 2008 15:20:25 -0400 |
Yoshua Bengio |
Moved incomplete stuff to sandbox
|
Sat, 19 Jul 2008 17:57:46 -0400 |
Yoshua Bengio |
Debugging kernel regression
|
Sat, 19 Jul 2008 14:26:24 -0400 |
Yoshua Bengio |
Fixed incorrect handling of slice column specifications in ArrayDataSet
|
Sat, 19 Jul 2008 14:18:35 -0400 |
Yoshua Bengio |
oops removed debug print
|
Sat, 19 Jul 2008 14:12:41 -0400 |
Yoshua Bengio |
Added __len__ to HStackedDataSet and replaced default len() by sys.maxint instead of None
|
Sat, 19 Jul 2008 10:11:22 -0400 |
Yoshua Bengio |
Kernel regression learning algorithm
|
Tue, 15 Jul 2008 12:57:21 -0400 |
James Bergstra |
Removed feature of passing the file as a pathname from filetensor.{read, write}
|
Mon, 14 Jul 2008 16:48:02 -0400 |
James Bergstra |
added other_ops.py to nnet_ops; added basic tests, no docs.
|
Mon, 14 Jul 2008 13:48:41 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Fri, 11 Jul 2008 17:19:37 -0400 |
Joseph Turian |
Parameters are no longer global
|
Fri, 11 Jul 2008 16:34:46 -0400 |
Joseph Turian |
Can now do minibatch update
|
Fri, 11 Jul 2008 15:33:27 -0400 |
Joseph Turian |
Small bugfix
|
Fri, 11 Jul 2008 15:29:37 -0400 |
Joseph Turian |
Added noise functions
|
Fri, 11 Jul 2008 15:26:41 -0400 |
Joseph Turian |
Added cost functions
|
Fri, 11 Jul 2008 15:14:03 -0400 |
Joseph Turian |
Updated readme
|
Fri, 11 Jul 2008 15:13:44 -0400 |
Joseph Turian |
Autoassociator now seems to work
|
Fri, 11 Jul 2008 01:33:27 -0400 |
Joseph Turian |
XENT per instance
|
Thu, 10 Jul 2008 17:33:28 -0400 |
Joseph Turian |
Moved denoising AA to sandbox
|
Mon, 14 Jul 2008 13:48:36 -0400 |
Frederic Bastien |
corrected import as a file moved to sandbox
|
Thu, 10 Jul 2008 09:03:11 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Thu, 10 Jul 2008 02:10:23 -0400 |
Joseph Turian |
Globals are now parameters for the RBM model
|
Thu, 10 Jul 2008 01:17:40 -0400 |
Joseph Turian |
Added weight decay
|
Thu, 10 Jul 2008 00:51:32 -0400 |
Joseph Turian |
Debugging simple AA a bit
|
Wed, 09 Jul 2008 17:55:46 -0400 |
Yoshua Bengio |
Making linear_regression more robust
|
Wed, 09 Jul 2008 15:27:12 -0400 |
Joseph Turian |
* Added momentum.
|
Wed, 09 Jul 2008 00:29:16 -0400 |
Joseph Turian |
Small updates
|
Tue, 08 Jul 2008 23:59:57 -0400 |
Joseph Turian |
Cleaned up, added sparse_instance
|
Tue, 08 Jul 2008 21:42:21 -0400 |
Joseph Turian |
RBM minibatch works
|
Tue, 08 Jul 2008 20:48:56 -0400 |
Joseph Turian |
Better output
|
Tue, 08 Jul 2008 20:39:36 -0400 |
Joseph Turian |
Added init to sandbox
|
Tue, 08 Jul 2008 20:37:36 -0400 |
Joseph Turian |
Bug fixed in RBM
|
Tue, 08 Jul 2008 20:14:21 -0400 |
Joseph Turian |
Basic, broken RBM implementation
|
Tue, 08 Jul 2008 18:46:37 -0400 |
Joseph Turian |
merge
|
Tue, 08 Jul 2008 18:46:26 -0400 |
Joseph Turian |
Made sandbox directory
|
Tue, 08 Jul 2008 18:45:35 -0400 |
Joseph Turian |
More debugging
|
Tue, 08 Jul 2008 17:50:23 -0400 |
Yoshua Bengio |
merge
|
Tue, 08 Jul 2008 17:49:44 -0400 |
Yoshua Bengio |
First non-crashing draft of LinearRegression
|
Tue, 08 Jul 2008 17:41:45 -0400 |
Joseph Turian |
Renamed simple AA directory
|
Tue, 08 Jul 2008 17:41:26 -0400 |
Joseph Turian |
Debugging simple AA
|
Tue, 08 Jul 2008 17:08:23 -0400 |
Joseph Turian |
__str__ method
|
Tue, 08 Jul 2008 02:27:00 -0400 |
Joseph Turian |
Added a simple AA
|
Tue, 08 Jul 2008 02:00:14 -0400 |
Joseph Turian |
merge
|
Tue, 08 Jul 2008 02:00:00 -0400 |
Joseph Turian |
Switched back to margin loss
|
Tue, 08 Jul 2008 01:59:42 -0400 |
Joseph Turian |
Small fix
|
Tue, 08 Jul 2008 01:58:16 -0400 |
Joseph Turian |
Moved xent loss to nnet_ups
|
Tue, 08 Jul 2008 01:57:33 -0400 |
Joseph Turian |
Added xent loss
|
Wed, 09 Jul 2008 16:55:27 -0400 |
Frederic Bastien |
added function to load amat file
|
Mon, 07 Jul 2008 12:27:06 -0400 |
Frederic Bastien |
small modif by yoshue
|
Mon, 07 Jul 2008 12:02:34 -0400 |
Yoshua Bengio |
fixing merge
|
Mon, 07 Jul 2008 10:09:37 -0400 |
Yoshua Bengio |
merge
|
Mon, 07 Jul 2008 10:08:35 -0400 |
Yoshua Bengio |
Redesigning linear_regression
|
Mon, 16 Jun 2008 17:47:36 -0400 |
Yoshua Bengio |
Automated merge with http://lgcm.iro.umontreal.ca/hg/pylearn
|
Tue, 03 Jun 2008 21:27:32 -0400 |
bengioy |
split LearningAlgorithm into OfflineLearningAlgorithm and OnlineLearningAlgorithm
|
Mon, 07 Jul 2008 02:15:14 -0400 |
Joseph Turian |
No update if there aren't any non-zeros
|
Mon, 07 Jul 2008 02:06:15 -0400 |
Joseph Turian |
Moved more logic into model.py
|
Mon, 07 Jul 2008 01:57:49 -0400 |
Joseph Turian |
Update doc
|
Mon, 07 Jul 2008 01:54:46 -0400 |
Joseph Turian |
Moved sparse_random_autoassociator from my repository
|
Fri, 04 Jul 2008 01:00:22 -0400 |
Joseph Turian |
Merge
|
Fri, 04 Jul 2008 01:00:11 -0400 |
Joseph Turian |
Removed featuremap.py, moved to common
|
Thu, 03 Jul 2008 23:55:39 -0400 |
Joseph Turian |
merge
|
Thu, 03 Jul 2008 23:52:56 -0400 |
Joseph Turian |
Removed common/
|
Thu, 03 Jul 2008 18:48:32 -0400 |
Joseph Turian |
Bugfix in common.misc.find_files
|
Thu, 03 Jul 2008 17:52:26 -0400 |
Joseph Turian |
merge
|
Thu, 03 Jul 2008 17:52:11 -0400 |
Joseph Turian |
Added to misc.file
|
Thu, 03 Jul 2008 00:14:42 -0400 |
Joseph Turian |
Added common.misc.utilsdir
|
Wed, 02 Jul 2008 23:56:51 -0400 |
Joseph Turian |
Added common.misc.homedir()
|
Wed, 02 Jul 2008 16:10:00 -0400 |
Joseph Turian |
common.misc.runcmd can now take input
|
Wed, 02 Jul 2008 15:42:42 -0400 |
Joseph Turian |
Improved runcmd
|
Tue, 01 Jul 2008 21:09:24 -0400 |
Joseph Turian |
Added common.misc.runcmd
|
Thu, 19 Jun 2008 16:27:02 -0400 |
Joseph Turian |
Added common.string
|
Thu, 19 Jun 2008 16:18:37 -0400 |
Joseph Turian |
Added more functions
|
Thu, 19 Jun 2008 16:12:29 -0400 |
Joseph Turian |
Added common directory
|
Thu, 19 Jun 2008 12:35:41 -0400 |
Thierry Bertin-Mahieux |
dataset__call__() returns a FieldsSubsetDataSet, so still a subset of fields, but not cached any more. I added the function dataset.cached_fields_subset(self,*fieldnames) that returns the old version, cached, in case someone needs it. Current behaviour passes the tests.
|
Tue, 17 Jun 2008 17:12:43 -0400 |
Thierry Bertin-Mahieux |
Cached dataset seems debug, using n_batches... is n_batches around to stay?
|
Tue, 17 Jun 2008 16:50:35 -0400 |
Frederic Bastien |
code cleanup
|
Tue, 17 Jun 2008 16:47:33 -0400 |
Frederic Bastien |
debugged RenamedFieldsDataSet
|
Tue, 17 Jun 2008 16:20:17 -0400 |
Frederic Bastien |
Can give test name in debug mode. This will execute on the gived test name.
|
Tue, 17 Jun 2008 16:09:59 -0400 |
Frederic Bastien |
added test for ds.subset()
|
Tue, 17 Jun 2008 14:59:10 -0400 |
Frederic Bastien |
corrected test_RenamedFieldsDataSet. It still fail, but this should be du to bug in RenamedFieldsDataSet.
|
Tue, 17 Jun 2008 14:46:15 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Tue, 17 Jun 2008 14:33:15 -0400 |
Yoshua Bengio |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Tue, 17 Jun 2008 14:32:54 -0400 |
Yoshua Bengio |
Added test for dataset/RenamedFieldsDataSet
|
Tue, 17 Jun 2008 14:46:10 -0400 |
Frederic Bastien |
bugfix, MinibatchDataSet.minibatches_nowrap() must raise StopIteration when needed
|
Tue, 17 Jun 2008 14:45:22 -0400 |
Frederic Bastien |
added test for ds.subset
|
Tue, 17 Jun 2008 14:32:03 -0400 |
Frederic Bastien |
fix test for __getitem__
|
Tue, 17 Jun 2008 13:33:17 -0400 |
Frederic Bastien |
corrected test for dataset.minibatches()
|
Tue, 17 Jun 2008 11:41:01 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Mon, 16 Jun 2008 17:26:51 -0400 |
Thierry Bertin-Mahieux |
n_minibatches in ArrayDataSet automatically computed
|
Mon, 16 Jun 2008 17:17:50 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Mon, 16 Jun 2008 17:17:01 -0400 |
Thierry Bertin-Mahieux |
debugging when fieldnames = None, now -> fieldnames = fieldNames()
|
Mon, 16 Jun 2008 17:07:44 -0400 |
Frederic Bastien |
Automated merge with ssh://projects@lgcm.iro.umontreal.ca/hg/pylearn
|
Mon, 16 Jun 2008 16:59:35 -0400 |
Thierry Bertin-Mahieux |
sorry for all the debugging, this push should be the good one (and damn you *self*)
|
Mon, 16 Jun 2008 16:52:39 -0400 |
Thierry Bertin-Mahieux |
debug in an assert of minibatches
|
Mon, 16 Jun 2008 17:07:41 -0400 |
Frederic Bastien |
bugfix in RenamedDataSet
|
Mon, 16 Jun 2008 16:44:11 -0400 |
Thierry Bertin-Mahieux |
redone my previous hack in MinibatchToSingleExampleIterator, tests should work again
|
Mon, 16 Jun 2008 16:38:03 -0400 |
Thierry Bertin-Mahieux |
IMPORTANT: minibatches now returns minibatch_nowrap with a minimum of assert before. Should implement the good behavior, e.g. returning only complete batches and let the user figure out what he wants.
|
Mon, 16 Jun 2008 16:11:36 -0400 |
Thierry Bertin-Mahieux |
merge
|
Mon, 16 Jun 2008 16:03:16 -0400 |
Thierry Bertin-Mahieux |
little hack in MiniBatchToSingleExampleIterator, there was a problem which I think was not a bug, we were receiving [array(3)] and everything was crashing. Hack is kinda slow
|
Mon, 16 Jun 2008 16:06:59 -0400 |
Yoshua Bengio |
Added untested RenamedFieldsDataSet
|
Mon, 16 Jun 2008 12:57:32 -0400 |
Frederic Bastien |
added file that was missing in commit 9e96fe8b955c
|
Fri, 13 Jun 2008 15:26:35 -0400 |
Olivier Breuleux |
made ExampleWiseMean Op
|
Fri, 13 Jun 2008 11:14:59 -0400 |
Thierry Bertin-Mahieux |
wrote back _cache
|
Thu, 12 Jun 2008 20:54:49 -0400 |
James Bergstra |
- the cut and paste between file and dir conditions is always a bad thing
|
Thu, 12 Jun 2008 17:12:45 -0400 |
Thierry Bertin-Mahieux |
version works with file and folder, returns null if not in hg. Also a function to get all modules, but seems to get junk at the same time
|
Thu, 12 Jun 2008 12:45:42 -0400 |
Thierry Bertin-Mahieux |
small bugs fixed with NArrayDataSet
|
Thu, 12 Jun 2008 12:35:47 -0400 |
Thierry Bertin-Mahieux |
NArraysDataSet improved, use arrays instead of matrix, also a dictionnary of field indexes
|
Wed, 11 Jun 2008 17:11:37 -0400 |
Thierry Bertin-Mahieux |
bug fixed when initializing NArraysDataSet with 1-d arrays. This now raises an Exception
|
Wed, 11 Jun 2008 17:05:56 -0400 |
Thierry Bertin-Mahieux |
bug fixed when one matrix is an array, a 1-d matrix
|
Wed, 11 Jun 2008 16:59:03 -0400 |
Thierry Bertin-Mahieux |
NArraysDataSet, a generalization ArrayDataSet where every field is a ndarray, is implemented. Not really tested aside basic stuff...
|
Wed, 11 Jun 2008 16:40:47 -0400 |
Thierry Bertin-Mahieux |
doc updated regarding __getitem__ returning LookupList and .subset returning a DataSet
|
Wed, 11 Jun 2008 16:28:09 -0400 |
Thierry Bertin-Mahieux |
getitem in ArrayDataSet is set up again, supposed to be faster than default one, has been tested agains the default behaviour. In particular, now always return a LookupList
|
Wed, 11 Jun 2008 16:26:41 -0400 |
Thierry Bertin-Mahieux |
test to compare overriden __getitem__ implemented, tested on ArrayDataSet.__getitem__
|