| 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.
|
| Tue, 06 May 2008 14:01:22 -0400 |
Frederic Bastien |
restructuring and added test
|
| Tue, 06 May 2008 13:57:36 -0400 |
Frederic Bastien |
in ArrayDataSet.__init__ if a columns is an index, we change it to be a list that containt only this index. This way, we remove the special case where the columns is an index for all subsequent call.
|
| Tue, 06 May 2008 13:50:54 -0400 |
Frederic Bastien |
bugfix in DataSet.minibatch to correctly wrap in all corner case.
|
| Tue, 06 May 2008 10:53:28 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Tue, 06 May 2008 10:53:21 -0400 |
Frederic Bastien |
added test and some restructuring for futur use
|
| Tue, 06 May 2008 10:52:45 -0400 |
Frederic Bastien |
removed duplicated example in comment
|
| Mon, 05 May 2008 17:44:49 -0400 |
Frederic Bastien |
corrected the use of .all()
|
| Mon, 05 May 2008 18:14:44 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
| Mon, 05 May 2008 18:14:32 -0400 |
Yoshua Bengio |
Finished first draft of TLearner
|
| Mon, 05 May 2008 17:13:53 -0400 |
Frederic Bastien |
corrected test from discution about the syntax with Yoshua
|
| Mon, 05 May 2008 17:13:07 -0400 |
Frederic Bastien |
corrected comment
|
| Mon, 05 May 2008 16:54:16 -0400 |
Frederic Bastien |
more test and refactoring
|
| Mon, 05 May 2008 14:51:41 -0400 |
Frederic Bastien |
bugfix as numpy numpy don't support self.data[[i1,...],[i2,...]] when their is more then two i1 and i2
|
| Mon, 05 May 2008 14:39:04 -0400 |
Frederic Bastien |
removed print
|
