- 24 Apr, 2020 1 commit
-
-
Yuhao Zhang authored
* Guard the unsafe tf.exp to prevent Inf cost * Update run_lfads.py Add the hyperparameter `_clip_value` to resolve the issue in the prototype example
-
- 18 Jun, 2018 1 commit
-
-
Dan O'Shea authored
-
- 24 May, 2018 1 commit
-
-
Dan O'Shea authored
-
- 22 Mar, 2018 1 commit
-
-
Dan O'Shea authored
-
- 03 Feb, 2018 3 commits
-
-
Dan O'Shea authored
-
Dan O'Shea authored
-
Dan O'Shea authored
For stitched models, the readin matrices and bias vectors are initialized to the "alignment" matrix and bias specified in each dataset's .h5 file. If do_train_readin is True, these will be trainable, and if not, they will be fixed.
-
- 26 Nov, 2017 1 commit
-
-
Chethan Pandarinath authored
-
- 21 Sep, 2017 1 commit
-
-
Neal Wu authored
-
- 27 Jul, 2017 2 commits
-
-
Dan O'Shea authored
-
Dan O'Shea authored
-
- 21 Jul, 2017 1 commit
-
-
David Sussillo authored
Made PCA bias work for input alignment. Fixed output matrix to pinv, added gaussian example, fixed output gaussian param inits, updated README
-
- 18 Jul, 2017 1 commit
-
-
Allen Lavoie authored
-
- 12 Jul, 2017 1 commit
-
-
Jasmine authored
-
- 22 Jun, 2017 1 commit
-
-
Jasmine authored
-