Mercurial > pylearn
changeset 1069:16ea3e5c5a7a
api_optimization: Couple questions
author | Olivier Delalleau <delallea@iro> |
---|---|
date | Fri, 10 Sep 2010 10:28:34 -0400 |
parents | 9fe0f0755b03 |
children | 79eb0016f333 |
files | doc/v2_planning/api_optimization.txt |
diffstat | 1 files changed, 8 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/doc/v2_planning/api_optimization.txt Fri Sep 10 10:01:53 2010 -0400 +++ b/doc/v2_planning/api_optimization.txt Fri Sep 10 10:28:34 2010 -0400 @@ -1,7 +1,7 @@ Optimization API ================ -Members: Bergstra, Lamblin, Dellaleau, Glorot, Breuleux, Bordes +Members: Bergstra, Lamblin, Delalleau, Glorot, Breuleux, Bordes Leader: Bergstra @@ -94,5 +94,12 @@ """ +OD: Could it be more convenient for x0 to be a list? +OD: Why make a difference between iterative and one-shot versions? A one-shot + algorithm can be seen as an iterative one that stops after its first + iteration. The difference I see between the two interfaces proposed here + is mostly that one relies on Theano while the other one does not, but + hopefully a non-Theano one can be created by simply wrapping around the + Theano one.