# HG changeset patch
# User Razvan Pascanu <r.pascanu@gmail.com>
# Date 1285263890 14400
# Node ID 70ca63c056721819ce4adb7a6410da03dd470163
# Parent  ab1db1837e989d4402647e90142b986636cc98b8
 comment on OD's reply

diff -r ab1db1837e98 -r 70ca63c05672 doc/v2_planning/arch_src/plugin_JB_comments_YB.txt
--- a/doc/v2_planning/arch_src/plugin_JB_comments_YB.txt	Thu Sep 23 13:36:04 2010 -0400
+++ b/doc/v2_planning/arch_src/plugin_JB_comments_YB.txt	Thu Sep 23 13:44:50 2010 -0400
@@ -105,3 +105,10 @@
 I am not convinced about is that we should also use it to write a standard
 serial machine learning algorithm (e.g. DBN training with fixed
 hyper-parameters).
+
+RP replies : What do you understand by writing down a DBN. I believe the
+structure and so on ( selecting the optimizers) shouldn't be done using this
+approach. You will start using this syntax to do early stopping, to decide the
+order of pre-training the layers. In my view you get something like
+pretrain_layer1, pretrain_layer2, finetune_one_step and then starting using
+James framework. Are you thinking in the same terms ?