# HG changeset patch # User Razvan Pascanu # Date 1284303249 14400 # Node ID a80b296eb0df252573e45b287c046af0d527e452 # Parent f1521635652237e6a9660e6f435dcd3ba1153ba9 I removed big picture from the description of the neural network committee diff -r f15216356522 -r a80b296eb0df doc/v2_planning/neural_net.txt --- a/doc/v2_planning/neural_net.txt Sat Sep 11 21:42:38 2010 -0400 +++ b/doc/v2_planning/neural_net.txt Sun Sep 12 10:54:09 2010 -0400 @@ -12,7 +12,12 @@ Objective ( Razvan) --------- -Come up with a big picture of how things work together. The way I see it personaly, -we should pick "random" interfaces for any component for which there is no one yet, -and come with pseudo-code for some tasks + text describing all details. +Come up with a description of how to write learners ( how to combine +optimizer, structure, error measure, how to talk to datasets, tasks ( if there +is anything like a dataset object in your view) and so on). +o The way I see it personaly, we should pick "random" interfaces for any component +for which there is no one yet, or change the interface to answer our needs. +If our description of how these things get together. I would say come up with +pseudo-code for some tasks ( that vary as much as possible) + text describing +all the missing details.