Mercurial > pylearn

changeset 1105:546bd0ccb0e4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
dataset: Question about shared variables
author Olivier Delalleau <delallea@iro>
date Mon, 13 Sep 2010 22:06:23 -0400
parents 5e6d7d9e803a
children 21d25bed2ce9
files doc/v2_planning/dataset.txt
diffstat 1 files changed, 5 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- a/doc/v2_planning/dataset.txt	Mon Sep 13 20:21:23 2010 -0400
+++ b/doc/v2_planning/dataset.txt	Mon Sep 13 22:06:23 2010 -0400
@@ -338,3 +338,8 @@
 framework that I have in mind, which was spattered around in the learner.txt
 and some of my previous emails. I think it shares a lot with James concepts, 
 since it follows quite closely the concepts behind Theano.
+
+OD asks: Ok, so why would the dataset have to be responsible for providing a
+shared variable? Why wouldn't the learner just create this shared variable
+internally and copy into it the data provided by the dataset?
+