Matt Graham a353526790 Adding augmented MNIST data provider.		2016-10-20 13:26:09 +01:00
..
__init__.py	Moving default seed to package level and adding author metadata.	2016-09-19 11:14:10 +01:00
data_providers.py	Adding augmented MNIST data provider.	2016-10-20 13:26:09 +01:00
errors.py	Applying softmax stability fix to cost gradient.	2016-10-20 13:23:19 +01:00
initialisers.py	Fixing typo in initialiser assert.	2016-10-10 10:09:29 +01:00
layers.py	Using more stable softmax implementation by subtracting max.	2016-10-18 13:54:39 +01:00
learning_rules.py	Bug fix: incorrect use of zip in MomentumLearningRule.	2016-10-12 23:11:38 +01:00
models.py	Removing final backpropagation of gradients to inputs as unnecessary.	2016-10-10 09:27:02 +01:00
optimisers.py	Dealing with case where number of epochs less than stats interval.	2016-10-17 23:32:23 +01:00
schedulers.py	Adding new schedulers module.	2016-10-10 09:23:53 +01:00