--- a/gradient_learner.py	Mon Apr 07 20:44:37 2008 -0400
+++ b/gradient_learner.py	Wed Apr 09 18:27:13 2008 -0400
@@ -9,9 +9,9 @@
     Base class for gradient-based optimization of a training criterion
     that can consist in two parts, an additive part over examples, and
     an example-independent part (usually called the regularizer).
-    The user provides a Theano formula that maps the fields of a training example
-    and parameters to output fields (for the use function), one of which must be a cost
-    that is the training criterion to be minimized. Subclasses implement
+    The user provides a Theano formula that maps the fields of a minibatch (each being a tensor with the
+    same number of rows = minibatch size) and parameters to output fields (for the use function), one of which
+    must be a cost that is the training criterion to be minimized. Subclasses implement
     a training strategy that uses the Theano formula to compute gradients and
     to compute outputs in the update method.
     The inputs, parameters, and outputs are lists of Theano tensors,
@@ -55,6 +55,6 @@
         if not self.use_functions.has_key(use_function_key):
             self.use_function[use_function_key]=Function(input_fields,output_fields)
         use_function = self.use_functions[use_function_key]
-        # return a virtual dataset that computes the outputs on demand
-        return input_dataset.apply_function(use_function,input_fields,output_fields,copy_inputs,accept_minibatches=???)
+        # return a dataset that computes the outputs
+        return input_dataset.applyFunction(use_function,input_fields,output_fields,copy_inputs,compute_now=True)