Mercurial > pylearn

diff sparse_random_autoassociator/main.py @ 381:e4473d9697d7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added xent loss
author Joseph Turian <turian@gmail.com>
date Tue, 08 Jul 2008 01:57:33 -0400
parents 75bab24bb2d8
children
line wrap: on
line diff
--- a/sparse_random_autoassociator/main.py	Mon Jul 07 02:15:14 2008 -0400
+++ b/sparse_random_autoassociator/main.py	Tue Jul 08 01:57:33 2008 -0400
@@ -20,6 +20,8 @@
     xnonzero magnitude (this may be a limitation). Hence, all nonzeroes
     are equally important to exceed the maximum yzero.
 
+    (Alternately, there is a commented out binary xent loss.)
+
     LIMITATIONS:
        - Only does pure stochastic gradient (batchsize = 1).
        - Loss is irrespective of the xnonzero magnitude.