|
|
9f4b494bf2
|
feedback transformer
|
2021-01-09 07:28:25 +05:30 |
|
|
|
ce190701e8
|
global step
|
2021-01-07 21:11:50 +05:30 |
|
|
|
c124348b14
|
gradient clipping
|
2021-01-07 13:33:32 +05:30 |
|
|
|
dfefde657b
|
no loss smoothing
|
2021-01-07 12:02:19 +05:30 |
|
|
|
b9da12ee3f
|
d_model
|
2021-01-06 17:24:09 +05:30 |
|
|
|
605ad0fdde
|
minor improvements
|
2021-01-03 14:39:01 +05:30 |
|
|
|
4cb730d579
|
fix
|
2021-01-03 14:33:16 +05:30 |
|
|
|
a962cc320e
|
fix
|
2021-01-03 14:28:07 +05:30 |
|
|
|
9907e03742
|
typo fix
|
2021-01-03 14:19:52 +05:30 |
|
|
|
6fe86efdff
|
badgeg
|
2021-01-03 12:16:01 +05:30 |
|
|
|
927acc2d81
|
hypernetworks link
|
2021-01-03 11:22:02 +05:30 |
|
|
|
979b01adc2
|
update experiment
|
2021-01-03 11:20:30 +05:30 |
|
|
|
bead174ed4
|
notebook
|
2021-01-03 11:12:55 +05:30 |
|
|
|
600c8590f4
|
hyperlstm notes
|
2021-01-03 11:07:12 +05:30 |
|
|
|
7d3c6fcd41
|
lstm chunk
|
2020-12-28 16:14:12 +05:30 |
|
|
|
814fd565c0
|
hyper lstm experiment
|
2020-12-28 16:02:47 +05:30 |
|
|
|
52d5b5fbf6
|
auto regression common exp
|
2020-12-27 07:35:35 +05:30 |
|
|
|
4fe8392a8d
|
auto regression common exp
|
2020-12-27 07:30:20 +05:30 |
|
|
|
c64b98e390
|
basic auto regression experiment for reuse
|
2020-12-26 21:12:44 +05:30 |
|
|
|
a6502de621
|
shuffle data
|
2020-12-26 20:46:58 +05:30 |
|
|
|
716dda5f3b
|
fix lr
|
2020-12-26 16:44:11 +05:30 |
|
|
|
48277e9334
|
hyperlstm
|
2020-12-26 15:49:44 +05:30 |
|
|
|
b05faa9b98
|
default warm up
|
2020-12-23 13:57:34 +05:30 |
|
|
|
634809af3c
|
noam chart fix
|
2020-12-23 13:52:08 +05:30 |
|
|
|
799a62a4fc
|
underset fix
|
2020-12-21 21:33:55 +05:30 |
|
|
|
625e250351
|
fix \u
|
2020-12-21 08:54:00 +05:30 |
|
|
|
8c7d5f549a
|
remove badge
|
2020-12-19 19:01:56 +05:30 |
|
|
|
040f42d357
|
remove badge
|
2020-12-19 18:57:47 +05:30 |
|
|
|
ac77ce006a
|
mha explanation
|
2020-12-18 20:58:56 +05:30 |
|
|
|
8078061c51
|
🐛 ada belief fix
|
2020-12-16 14:12:38 +05:30 |
|
|
|
2c1e6c721d
|
🐛 lstm fix
|
2020-12-16 11:55:36 +05:30 |
|
|
|
91d917ae00
|
optimizers path fix
|
2020-12-14 10:23:58 +05:30 |
|
|
|
ef922321be
|
optimizers
|
2020-12-14 09:33:07 +05:30 |
|
|
|
5b1897b792
|
optimizers
|
2020-12-14 09:31:11 +05:30 |
|
|
|
19ed54c6e1
|
radam plot
|
2020-12-10 16:02:01 +05:30 |
|
|
|
14bed4c432
|
radam
|
2020-12-10 14:18:07 +05:30 |
|
|
|
10ee239a14
|
unoptimized adam
|
2020-12-10 10:51:19 +05:30 |
|
|
|
4d58757671
|
unoptimized adam
|
2020-12-10 10:50:18 +05:30 |
|
|
|
1f75f42fb2
|
yaml configs
|
2020-12-10 10:05:06 +05:30 |
|
|
|
443458e812
|
summaries
|
2020-12-10 08:42:06 +05:30 |
|
|
|
b7d5c5db75
|
optimizer links
|
2020-12-08 07:12:17 +05:30 |
|
|
|
791cd1222d
|
https links
|
2020-12-07 22:27:58 +05:30 |
|
|
|
22fb0b79a2
|
colab
|
2020-12-07 10:15:14 +05:30 |
|
|
|
116f1645f8
|
amsgrad
|
2020-12-07 10:07:10 +05:30 |
|
|
|
ca1cea7009
|
amsgrad synthetic experiment
|
2020-12-06 15:23:57 +05:30 |
|
|
|
264bdc8eeb
|
math fix
|
2020-12-06 08:54:21 +05:30 |
|
|
|
dc48f0a4e1
|
notes
|
2020-12-06 08:14:56 +05:30 |
|
|
|
c71a5c5ae2
|
adam comments
|
2020-12-06 07:22:36 +05:30 |
|
|
|
874c238651
|
📚 adam notes
|
2020-12-05 11:21:11 +05:30 |
|
|
|
27b3922647
|
optimizer configs
|
2020-12-03 20:28:56 +05:30 |
|
