Mercurial > pylearn

changeset 1101:b422cbaddc52

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
v2planning - minor edits to use_cases
author James Bergstra <bergstrj@iro.umontreal.ca>
date Mon, 13 Sep 2010 13:42:26 -0400
parents 153cf820a975
children e7c52923f122
files doc/v2_planning/use_cases.txt
diffstat 1 files changed, 3 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/doc/v2_planning/use_cases.txt	Mon Sep 13 13:41:53 2010 -0400
+++ b/doc/v2_planning/use_cases.txt	Mon Sep 13 13:42:26 2010 -0400
@@ -66,6 +66,7 @@
             classification_accuracy(
                 examples=MNIST.validation_dataset,
                 function=as_classifier('learner_obj'))),
+
         step_fn = vm_lambda(('learner_obj',),
             sgd_step_fn(
                 parameters = vm_getattr('learner_obj', 'params'),
@@ -113,7 +114,7 @@
             initial_model=alloc_model('param1', 'param2'),
             burnin=100,
             score_fn = vm_lambda(('learner_obj',),
-                graph=classification_error(
+                classification_error(
                     function=as_classifier('learner_obj'),
                     dataset=MNIST.subset(validation_set))),
             step_fn = vm_lambda(('learner_obj',),
@@ -145,7 +146,7 @@
 extending the symbolic program, and calling the extended function.
 
     vm.call(
-        [pylearn.min(model.weights) for model in trained_models], 
+        [pylearn.min(pylearn_getattr(model, 'weights')) for model in trained_models], 
         param1=1, param2=2)
 
 If this is run after the previous calls: