Matt Graham
|
adf7a0ffee
|
Adding further dataset details to CIFAR intro notebook.
|
2017-01-22 12:44:58 +00:00 |
|
Matt Graham
|
5556963490
|
Updating MSD data providers to reshape and upcast.
|
2017-01-22 12:44:24 +00:00 |
|
Matt Graham
|
8507224d90
|
Adding CIFAR-10 and CIFAR-100 intro notebook.
|
2017-01-21 19:44:30 +00:00 |
|
Matt Graham
|
822b946033
|
Adding MSD data providers.
|
2017-01-21 19:34:01 +00:00 |
|
Matt Graham
|
510a1ca7be
|
Adding CIFAR data providers.
|
2017-01-19 18:51:18 +00:00 |
|
Matt Graham
|
c4a662465e
|
Clarifying initializers description: notebook save failed in previous commit.
|
2017-01-19 10:49:10 +00:00 |
|
Matt Graham
|
223bd971d1
|
Clarifying initializers description.
|
2017-01-18 13:14:03 +00:00 |
|
Matt Graham
|
23e015085f
|
Adding optional contrib modules exercise.
|
2017-01-17 18:26:33 +00:00 |
|
Matt Graham
|
e0262e43fc
|
Adding TensorFlow install instructions: attempt 2.
|
2017-01-17 12:57:16 +00:00 |
|
Matt Graham
|
dfd7414791
|
Merge branch 'mlp2016-7/master' of https://github.com/CSTR-Edinburgh/mlpractical into mlp2016-7/master
|
2017-01-17 12:55:28 +00:00 |
|
Matt Graham
|
8b756fce5d
|
Adding TensorFlow install instructions.
|
2017-01-17 12:55:00 +00:00 |
|
Matt Graham
|
8390e4a822
|
Updating Autoencoders notebook with solutions.
|
2016-12-26 18:58:30 +00:00 |
|
Matt Graham
|
ca9f1e6424
|
Clearing outputs from TensorFlow intro notebook.
|
2016-12-22 23:52:30 +00:00 |
|
Matt Graham
|
ae666f895a
|
Adding figures for TensorFlow intro notebook.
|
2016-12-22 23:42:21 +00:00 |
|
Matt Graham
|
8c08b0d5ea
|
Adding TensorFlow introduction notebook.
|
2016-12-22 23:40:46 +00:00 |
|
Jonathan Jouty
|
6892424a43
|
Fix __repr__ implementation for SingleLayerModel (#46)
|
2016-11-22 22:21:45 +00:00 |
|
Matt Graham
|
d41063dca6
|
Rerunning dropout experiment with non-stochastic evaluation.
|
2016-11-09 19:58:26 +00:00 |
|
Matt Graham
|
77a96cfc01
|
Fixing use of global rng in DropoutLayer fprop.
|
2016-11-09 19:55:11 +00:00 |
|
Matt Graham
|
9c86d00078
|
Changing default optimiser behaviour to use non-stochastic evaluation for stochastic layers.
|
2016-11-09 19:51:33 +00:00 |
|
Matt Graham
|
d290f4513d
|
Fixing inconsistent channel ordering in constructor and docstring shape descriptions.
|
2016-11-09 19:47:42 +00:00 |
|
Matt Graham
|
60edabd261
|
Fixing missing bias term from model visualisation.
|
2016-11-05 22:21:44 +00:00 |
|
Matt Graham
|
905545fd23
|
Adding notebook for 7th lab on autoencoders.
|
2016-11-05 22:20:29 +00:00 |
|
Matt Graham
|
9bb4d7560b
|
Adding dropout and maxout layers to module.
|
2016-11-05 22:19:47 +00:00 |
|
Matt Graham
|
fa9ef33460
|
Adding dropout and maxout notebook answers.
|
2016-11-05 22:19:28 +00:00 |
|
Matt Graham
|
02e29ddcc6
|
Adding time-dependent learning rule schedulers.
|
2016-11-03 18:31:59 +00:00 |
|
Matt Graham
|
2b20484649
|
Adding adaptive learning rules.
|
2016-11-03 18:31:37 +00:00 |
|
Matt Graham
|
6f4aa5fd5f
|
Adding regularisation penalties module.
|
2016-11-03 18:28:57 +00:00 |
|
Matt Graham
|
057a25ed07
|
Adding autoencoder wrapper data provider.
|
2016-11-03 18:28:41 +00:00 |
|
Matt Graham
|
2a4364d226
|
Adding necessary imports.
|
2016-11-02 03:39:13 +00:00 |
|
Matt Graham
|
534c4744ca
|
Fixing incorrect use of module relative class reference.
|
2016-11-02 03:39:13 +00:00 |
|
Matt Graham
|
891b942890
|
Merge branch 'mlp2016-7/master' of https://github.com/CSTR-Edinburgh/mlpractical into mlp2016-7/master
|
2016-11-02 02:55:37 +00:00 |
|
Matt Graham
|
a575efb0ee
|
Adding instructions on running notebooks remotely.
|
2016-11-02 02:55:10 +00:00 |
|
Matt Graham
|
e0114b9aab
|
Adding notebook with convolutional layer tests.
|
2016-11-02 01:14:27 +00:00 |
|
Matt Graham
|
da9ee58609
|
Adding reshape layer.
|
2016-11-02 01:13:22 +00:00 |
|
Matt Graham
|
d5ae8b2caf
|
Merge pull request #43 from jfainberg/patch-1
Minor typos in momentum docstring
|
2016-10-29 21:17:24 +01:00 |
|
Joachim
|
bea3502210
|
Minor typos in momentum docstring
|
2016-10-29 15:57:00 +01:00 |
|
Matt Graham
|
a6f775b1ff
|
Adding notebook for lab 6.
|
2016-10-27 21:43:35 +01:00 |
|
Matt Graham
|
1efe9de847
|
Adding code for lab 5 notebook answers.
|
2016-10-27 21:43:08 +01:00 |
|
Matt Graham
|
95d4028bb7
|
Adding stochastic layer functionality in preparation for dropout implementation.
|
2016-10-27 21:36:57 +01:00 |
|
Matt Graham
|
7e1250a82b
|
Adding bash script to secure Jupyter notebook server on DICE.
|
2016-10-27 21:35:55 +01:00 |
|
Matt Graham
|
dfcce94242
|
Clarifying docstring in scheduler.
|
2016-10-27 11:24:00 +01:00 |
|
Matt Graham
|
ae999b43e4
|
Fixing spacing typo.
|
2016-10-21 22:07:41 +01:00 |
|
Matt Graham
|
9a182d4be1
|
Correcting regularisation coefficient values to test.
|
2016-10-21 22:07:25 +01:00 |
|
Matt Graham
|
cf6417f917
|
Removing old transfer function notebook.
|
2016-10-21 22:06:37 +01:00 |
|
Matt Graham
|
586c7477eb
|
Removing old regularisation notebook.
|
2016-10-21 01:25:08 +01:00 |
|
Matt Graham
|
167508cc63
|
Adding new lab 5 notebook.
|
2016-10-21 01:24:37 +01:00 |
|
Matt Graham
|
ab060d556c
|
Switching to parameter penalty rather than cost naming.
|
2016-10-21 01:24:04 +01:00 |
|
Matt Graham
|
a353526790
|
Adding augmented MNIST data provider.
|
2016-10-20 13:26:09 +01:00 |
|
Matt Graham
|
a021ce585b
|
Applying softmax stability fix to cost gradient.
|
2016-10-20 13:23:19 +01:00 |
|
Matt Graham
|
b4b00e0c65
|
Using more stable softmax implementation by subtracting max.
|
2016-10-18 13:54:39 +01:00 |
|