# HG changeset patch
# User Yoshua Bengio <bengioy@iro.umontreal.ca>
# Date 1284560735 14400
# Node ID 0f184b5e7a3f58508e1521fe864f177e6c8a91a5
# Parent  1a1c0c3adccaeaa9ae6f56b68c19f197f3497faf
YB: comment on minibatches for dataset.txt

diff -r 1a1c0c3adcca -r 0f184b5e7a3f doc/v2_planning/dataset.txt
--- a/doc/v2_planning/dataset.txt	Wed Sep 15 09:42:11 2010 -0400
+++ b/doc/v2_planning/dataset.txt	Wed Sep 15 10:25:35 2010 -0400
@@ -264,6 +264,11 @@
 use numpy arrays (for numeric data) or lists (for anything else) to store
 mini-batches' data. So I vote for 'no'.
 
+YB: I agree that a mini-batch should definitely be safely assumed
+to fit in memory. That makes it at least in principle semantically
+different from a dataset. But barring that restriction, it might
+share of the properties of a dataset.
+
 A dataset is a learner
 ~~~~~~~~~~~~~~~~~~~~~~