log

age author description
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