Mercurial > pylearn
annotate cost.py @ 450:117e5b09cf31
Added an XlogX op.
| author | Joseph Turian <turian@gmail.com> |
|---|---|
| date | Thu, 04 Sep 2008 14:46:17 -0400 |
| parents | 2bb67e978c28 |
| children | d99fefbc9324 |
| rev | line source |
|---|---|
| 413 | 1 """ |
| 2 Cost functions. | |
| 439 | 3 |
| 4 @note: All of these functions return one cost per example. So it is your | |
| 5 job to perform a tensor.sum over the individual example losses. | |
| 413 | 6 """ |
| 7 | |
| 415 | 8 import theano.tensor as T |
| 9 | |
| 413 | 10 def quadratic(target, output, axis=1): |
| 11 return T.mean(T.sqr(target - output), axis) | |
| 12 | |
| 13 def cross_entropy(target, output, axis=1): | |
| 448 | 14 """ |
| 15 @todo: This is essentially duplicated as nnet_ops.binary_crossentropy | |
| 449 | 16 @warning: OUTPUT and TARGET are reversed in nnet_ops.binary_crossentropy |
| 448 | 17 """ |
|
434
0f366ecb11ee
log2->log in cost
Olivier Breuleux <breuleuo@iro.umontreal.ca>
parents:
415
diff
changeset
|
18 return -T.mean(target * T.log(output) + (1 - target) * T.log(1 - output), axis=axis) |