December 7, 2018
View fa4696e

fix plotting resolution for larger scaled learnerND

Jorn Hoofwijk authored on 07/12/2018 09:36:21 • Bas Nijholt committed on 07/12/2018 17:06:03
View a0d5e69

fix example in doc-string of BalancingLearner.save

Bas Nijholt authored on 07/12/2018 16:49:59
View 31bebf0

implement own version of 'round' that speeds up the Learner1D by 30%

Bas Nijholt authored on 07/12/2018 12:00:13
View 669cf07

Merge branch '126--speed-up-learner1D' into 'master'

Bas Nijholt authored on 07/12/2018 11:42:53
View 4381a9e

Resolve "(Learner1D) improve time complexity"

Jorn Hoofwijk authored on 07/12/2018 11:42:53 • Bas Nijholt committed on 07/12/2018 11:42:53
December 5, 2018
View c0012a9

fix typo in 'uniform_loss' doc-string, closes #127

Bas Nijholt authored on 05/12/2018 13:47:11
November 28, 2018
View f38d20f

actually compute the dx by subtracting two DIFFERENT numbers

Jorn Hoofwijk authored on 28/11/2018 17:33:23 • Bas Nijholt committed on 28/11/2018 21:07:15
November 27, 2018
View 9c26669

fix bug with saving of the BalancingLearner

Bas Nijholt authored on 27/11/2018 13:59:26
November 26, 2018
View 06b9200

adhere to PEP008 by using absolute imports

Bas Nijholt authored on 26/11/2018 13:39:12
View 2f2e80d

Merge branch 'test_loss_functions' into 'master'

Bas Nijholt authored on 26/11/2018 13:26:22
View d2d955e

use math.isclose

Bas Nijholt authored on 23/11/2018 12:18:37
View 4da759f

run fewer points in 'test_learner_performance_is_invariant_under_scaling'

Bas Nijholt authored on 23/11/2018 12:04:58
View 38ff5e2

add '_recompute_losses_factor' such that we can set it in the test

Bas Nijholt authored on 23/11/2018 12:01:56
View d6b2187

add 'with_all_loss_functions' to 'run_with'

Bas Nijholt authored on 23/11/2018 11:41:52
View be74ad6

round the losses to 12 digits to make them equal

Bas Nijholt authored on 22/11/2018 18:58:19