Commit Graph

182 Commits

Author SHA1 Message Date
Connor Olding f60535aa01 generalize Adam-like optimizers 2019-02-03 14:30:03 +01:00
Connor Olding c6ebd02ea9 comply to PEP 8 2018-03-24 06:26:02 +01:00
Connor Olding a685db1489 add exact GELU activation 2018-03-22 12:02:17 +01:00
Connor Olding 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
Connor Olding ec71d4956e fix module leaking for real 2018-03-13 03:27:11 +01:00
Connor Olding 843524b80a move ActivityRegularizer to regularizer.py 2018-03-13 02:34:44 +01:00
Connor Olding b74e0941dc fix Swish inits 2018-03-12 02:17:28 +01:00
Connor Olding bd1e80b8de activation layers inherit a dummy class 2018-03-11 22:34:46 +01:00
Connor Olding cb4e6d3725 add Swish and SiLU activations 2018-03-11 03:34:00 +01:00
Connor Olding 91cdea3b26 fix inequalities in HardClip
oldest trick in the book
2018-03-10 05:03:26 +01:00
Connor Olding a6519f5455 improve notes on dependencies 2018-03-09 10:17:31 +01:00
Connor Olding bd4f2a9478 fix missing import for ActivityRegularizer 2018-03-09 10:09:50 +01:00
Connor Olding 9a45b26b7f add rough stratified k-folding utility class 2018-03-08 02:41:45 +01:00
Connor Olding 65bc9b8a6f optionally allow gradients to passthru Input layer 2018-03-08 02:40:56 +01:00
Connor Olding 4746103978 add HardClip activation layer 2018-03-08 02:40:42 +01:00
Connor Olding 44cae4ad50 add LookupLearner 2018-03-07 01:58:17 +01:00
Connor Olding 8abbb1e713 add NoiseInjector and NoiseMultiplier layers 2018-03-07 01:54:48 +01:00
Connor Olding 604ffb9fa1 add variant of L1L2 regularization using averages 2018-03-07 01:53:40 +01:00
Connor Olding 713fd2adbe add experimental soft-clipped optimizers 2018-03-07 01:52:26 +01:00
Connor Olding 3aa3b70a9f add AMSgrad optimizer 2018-03-07 01:30:04 +01:00
Connor Olding 0641c747c9 add Arcsinh activation 2018-03-07 01:29:48 +01:00
Connor Olding 8ce2ec1ad4 add missing import 2018-02-10 11:28:43 +01:00
Connor Olding 39bbf27860 add onehot utility function 2018-02-02 08:52:32 +01:00
Connor Olding e7783188bb tweak float exports 2018-02-02 08:51:39 +01:00
Connor Olding 169303813d basic PEP 8 compliance
rip readability
2018-01-22 19:40:36 +00:00
Connor Olding c81ce0afbb rename stuff and add a couple missing imports 2018-01-21 22:16:36 +00:00
Connor Olding bbdb91fcb1 merge and split modules into a package 2018-01-21 22:07:57 +00:00
Connor Olding db65fbdd62 add Neumann optimizer 2018-01-12 15:42:04 +00:00
Connor Olding 1ebb897f14 use @ operator 2017-10-19 04:12:16 +00:00
Connor Olding a85ee67780 allow CLRs to use optimizer's learning rate 2017-10-19 04:03:44 +00:00
Connor Olding 763246df98 add RMSpropCentered to model from config 2017-09-26 23:12:40 +00:00
Connor Olding 9bb26b1ec5 add Huber loss 2017-09-25 16:37:52 +00:00
Connor Olding eb16377ba6 add Adagrad optimizer 2017-09-25 16:06:45 +00:00
Connor Olding c964f143d2 not true 2017-09-25 07:12:19 +00:00
Connor Olding 5b6fd6259f update example 2017-09-25 06:28:59 +00:00
Connor Olding a760c4841b add fallback to optim.lr in AnnealingLearner 2017-09-25 06:10:54 +00:00
Connor Olding 916c6fe1f0 assert that rituals have been prepared 2017-09-25 06:10:04 +00:00
Connor Olding 615f43c550 support AddSign and PowerSign in config 2017-09-25 06:09:36 +00:00
Connor Olding fe54002671 remove DumbLearner 2017-09-25 06:09:07 +00:00
Connor Olding 9a7ffe5f0d add AddSign and PowerSign optimizers 2017-09-25 04:02:17 +00:00
Connor Olding 5c83f063be remove keras stuff so it won't show on google
bleh
2017-09-18 04:42:41 +00:00
Connor Olding d38e2076f0 allow multi-input and multi-output models 2017-09-16 18:28:05 +00:00
Connor Olding 3386869b30 move actreg tweaking into if statement
i was getting division by zero.
2017-09-16 17:33:47 +00:00
Connor Olding 65ba80bb96 skip over irrelevant nodes 2017-09-16 17:31:39 +00:00
Connor Olding dcbaef3032 use MomentumClip in warmup for stability 2017-09-16 17:30:52 +00:00
Connor Olding 7878f94f43 auto-increment loss filenames to stop clobbering 2017-09-16 17:30:02 +00:00
Connor Olding e22316a4c9 move losses into Model and refactor methods 2017-09-16 17:05:25 +00:00
Connor Olding 910facf98d move NLL to core 2017-08-05 10:59:05 +00:00
Connor Olding 0b9c1fe117 allow SGDR to anneal optimizer's learning rate
e.g. YellowFin
2017-08-05 10:43:38 +00:00
Connor Olding dbd6c31ea5 fix final rate calculation 2017-08-05 10:43:18 +00:00