# HG changeset patch # User Olivier Delalleau # Date 1285263364 14400 # Node ID ab1db1837e989d4402647e90142b986636cc98b8 # Parent fda31afc0df6f3200c0f4f029ab107d1ed8d8e82 JB's plugin: Reply to JB diff -r fda31afc0df6 -r ab1db1837e98 doc/v2_planning/arch_src/plugin_JB_comments_YB.txt --- a/doc/v2_planning/arch_src/plugin_JB_comments_YB.txt Thu Sep 23 13:29:05 2010 -0400 +++ b/doc/v2_planning/arch_src/plugin_JB_comments_YB.txt Thu Sep 23 13:36:04 2010 -0400 @@ -100,3 +100,8 @@ with a list of scripts and instructions for what to do with them (especially because the README often never gets written). +OD replies: I can see such a framework being useful for high-level experiment +design (the "big picture", or how to plug different components together). What +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).