Commit graph

204 commits

Author SHA1 Message Date
7f1d2afb02 add hinge losses 2019-03-22 12:54:20 +01:00
285bf1d96a move Confidence to experimental 2019-03-22 12:53:30 +01:00
0aba113cb7 update comments 2019-03-22 12:52:44 +01:00
e2530c17e5 clean up Ritual a little 2019-02-18 06:25:10 +01:00
69e6ec3fad add a convenient generator method to Learner 2019-02-18 06:23:05 +01:00
2b5798332d allow configuration of Neumann hyperparameters 2019-02-17 07:47:53 +01:00
c92082e07a fix momentum quantity in Neumann optimizer 2019-02-17 07:47:05 +01:00
5a07cdac32 add mixup variant of batchize 2019-02-11 20:30:31 +01:00
2cfcc9062e use the constant recommended by the paper 2019-02-06 18:41:55 +01:00
594483c6d4 correct "frequency" to "period" 2019-02-06 18:41:38 +01:00
50e0311051 allow passing model through Ritual init 2019-02-05 22:16:46 +01:00
fd2fc4bd76 begin rewriting Ritual 2019-02-05 06:09:35 +01:00
2c921d34c2 add Yogi optimizer 2019-02-05 04:19:48 +01:00
7deaa3c3f6 reword some comments 2019-02-05 04:19:14 +01:00
7227559912 reset learning rates in optimizers 2019-02-05 04:15:28 +01:00
bd07d983be add polynomial features layer 2019-02-05 04:13:56 +01:00
54ea41711b refactor gradient filtering 2019-02-03 15:10:43 +01:00
0d28882ef0 remove YellowFin because it's not worth maintaining 2019-02-03 15:03:03 +01:00
5fd2b7b546 remove old versions of optimizers 2019-02-03 14:43:04 +01:00
1e6887cdbd comment on Softmax alpha term 2019-02-03 14:31:34 +01:00
b8c40d2e2f rewrite some comments 2019-02-03 14:30:58 +01:00
94f27d6f2a add Adadelta optimizer 2019-02-03 14:30:47 +01:00
f60535aa01 generalize Adam-like optimizers 2019-02-03 14:30:03 +01:00
c6ebd02ea9 comply to PEP 8 2018-03-24 06:26:02 +01:00
a685db1489 add exact GELU activation 2018-03-22 12:02:17 +01:00
7161f983ab fix __name__ being incorrect due to extra __all__
this fixes tracebacks and checks for __main__,
among other things.
2018-03-17 14:09:15 +01:00
ec71d4956e fix module leaking for real 2018-03-13 03:27:11 +01:00
843524b80a move ActivityRegularizer to regularizer.py 2018-03-13 02:34:44 +01:00
b74e0941dc fix Swish inits 2018-03-12 02:17:28 +01:00
bd1e80b8de activation layers inherit a dummy class 2018-03-11 22:34:46 +01:00
cb4e6d3725 add Swish and SiLU activations 2018-03-11 03:34:00 +01:00
91cdea3b26 fix inequalities in HardClip
oldest trick in the book
2018-03-10 05:03:26 +01:00
a6519f5455 improve notes on dependencies 2018-03-09 10:17:31 +01:00
bd4f2a9478 fix missing import for ActivityRegularizer 2018-03-09 10:09:50 +01:00
9a45b26b7f add rough stratified k-folding utility class 2018-03-08 02:41:45 +01:00
65bc9b8a6f optionally allow gradients to passthru Input layer 2018-03-08 02:40:56 +01:00
4746103978 add HardClip activation layer 2018-03-08 02:40:42 +01:00
44cae4ad50 add LookupLearner 2018-03-07 01:58:17 +01:00
8abbb1e713 add NoiseInjector and NoiseMultiplier layers 2018-03-07 01:54:48 +01:00
604ffb9fa1 add variant of L1L2 regularization using averages 2018-03-07 01:53:40 +01:00
713fd2adbe add experimental soft-clipped optimizers 2018-03-07 01:52:26 +01:00
3aa3b70a9f add AMSgrad optimizer 2018-03-07 01:30:04 +01:00
0641c747c9 add Arcsinh activation 2018-03-07 01:29:48 +01:00
8ce2ec1ad4 add missing import 2018-02-10 11:28:43 +01:00
39bbf27860 add onehot utility function 2018-02-02 08:52:32 +01:00
e7783188bb tweak float exports 2018-02-02 08:51:39 +01:00
169303813d basic PEP 8 compliance
rip readability
2018-01-22 19:40:36 +00:00
c81ce0afbb rename stuff and add a couple missing imports 2018-01-21 22:16:36 +00:00
bbdb91fcb1 merge and split modules into a package 2018-01-21 22:07:57 +00:00
db65fbdd62 add Neumann optimizer 2018-01-12 15:42:04 +00:00