- 07 Feb, 2019 1 commit
-
-
Bas Nijholt authored
-
- 17 Dec, 2018 3 commits
-
-
Joseph Weston authored
-
-
-
- 14 Dec, 2018 1 commit
-
-
Bas Nijholt authored
-
- 11 Dec, 2018 2 commits
-
-
Joseph Weston authored
We use sortedcontainers 2.0 API.
-
Bas Nijholt authored
-
- 07 Dec, 2018 9 commits
-
-
Bas Nijholt authored
-
Bas Nijholt authored
-
Bas Nijholt authored
LearnerND scale output values before computing loss Closes #78 See merge request !128
-
-
-
Bas Nijholt authored
-
Bas Nijholt authored
-
Bas Nijholt authored
Resolve "(Learner1D) improve time complexity" Closes #126 and #104 See merge request !139
-
-
- 05 Dec, 2018 1 commit
-
-
Bas Nijholt authored
-
- 28 Nov, 2018 1 commit
-
-
- 27 Nov, 2018 1 commit
-
-
Bas Nijholt authored
-
- 26 Nov, 2018 10 commits
-
-
-
Bas Nijholt authored
test all the different loss functions in each test See merge request !135
-
Bas Nijholt authored
-
Bas Nijholt authored
-
Bas Nijholt authored
and have fewer xfailing tests
-
Bas Nijholt authored
-
Bas Nijholt authored
Then equal losses will be sorted on x-coordinates.
-
-
Bas Nijholt authored
-
Joseph Weston authored
make 'fname' a parameter to 'save' and 'load' only Closes #122 See merge request !133
-
- 23 Nov, 2018 4 commits
-
-
Bas Nijholt authored
-
Bas Nijholt authored
-
This simplifies the API by making sure that the filenames are only provided in one place (the calls to save and load). Closes #122
-
Bas Nijholt authored
-
- 22 Nov, 2018 7 commits
-
-
Bas Nijholt authored
* add 'curvature_loss_function' to the 'tutorial.custom_loss.rst' * fix header styling * fix doc-string
-
Bas Nijholt authored
-
Bas Nijholt authored
-
Bas Nijholt authored
-
Bas Nijholt authored
Resolve "(Learner1D) add possibility to use the direct neighbors in the loss" Closes #119 See merge request !131
-
-
-