Mercurial > pylearn
diff cost.py @ 484:3daabc7f94ff
Added Yoshua's explanation
author | Joseph Turian <turian@gmail.com> |
---|---|
date | Tue, 28 Oct 2008 01:33:27 -0400 |
parents | d99fefbc9324 |
children | 94a4c5b7293b |
line wrap: on
line diff
--- a/cost.py Tue Oct 28 00:23:53 2008 -0400 +++ b/cost.py Tue Oct 28 01:33:27 2008 -0400 @@ -3,6 +3,8 @@ @note: All of these functions return one cost per example. So it is your job to perform a tensor.sum over the individual example losses. + +@todo: It would be nice to implement a hinge loss, with a particular margin. """ import theano.tensor as T