--- a/sandbox/simple_autoassociator/globals.py	Fri Jul 11 15:33:27 2008 -0400
+++ b/sandbox/simple_autoassociator/globals.py	Fri Jul 11 16:34:46 2008 -0400
@@ -2,11 +2,11 @@
 Global variables.
 """
 
-#INPUT_DIMENSION = 1000
+INPUT_DIMENSION = 1000
 #INPUT_DIMENSION = 100
-INPUT_DIMENSION = 4
-#HIDDEN_DIMENSION = 10
-HIDDEN_DIMENSION = 1
+#INPUT_DIMENSION = 4
+HIDDEN_DIMENSION = 10
+#HIDDEN_DIMENSION = 1
 LEARNING_RATE = 0.1
 LR = LEARNING_RATE
 SEED = 666

--- a/sandbox/simple_autoassociator/graph.py	Fri Jul 11 15:33:27 2008 -0400
+++ b/sandbox/simple_autoassociator/graph.py	Fri Jul 11 16:34:46 2008 -0400
@@ -6,7 +6,7 @@
 from pylearn.nnet_ops import sigmoid, binary_crossentropy
 from theano import tensor as t
 from theano.tensor import dot
-x           = t.dvector()
+x           = t.dmatrix()
 w1          = t.dmatrix()
 b1          = t.dvector()
 w2          = t.dmatrix()

--- a/sandbox/simple_autoassociator/main.py	Fri Jul 11 15:33:27 2008 -0400
+++ b/sandbox/simple_autoassociator/main.py	Fri Jul 11 16:34:46 2008 -0400
@@ -7,9 +7,6 @@
        y   = sigmoid(dot(h, w2) + b2)
 
     Binary xent loss.
-
-    LIMITATIONS:
-       - Only does pure stochastic gradient (batchsize = 1).
 """
 
 
@@ -27,8 +24,8 @@
 model = model.Model()
 
 for i in xrange(100000):
-    # Select an instance
-    instance = nonzero_instances[i % len(nonzero_instances)]
+#    # Select an instance
+#    instance = nonzero_instances[i % len(nonzero_instances)]
 
-    # SGD update over instance
-    model.update(instance)
+    # Update over instance
+    model.update(nonzero_instances)

--- a/sandbox/simple_autoassociator/model.py	Fri Jul 11 15:33:27 2008 -0400
+++ b/sandbox/simple_autoassociator/model.py	Fri Jul 11 16:34:46 2008 -0400
@@ -13,20 +13,26 @@
 import random
 random.seed(globals.SEED)
 
+import pylearn.sparse_instance
+
 class Model:
     def __init__(self):
         self.parameters = parameters.Parameters(randomly_initialize=True)
 
-    def update(self, instance):
+#    def deterministic_reconstruction(self, x):
+#        (y, h, loss, gw1, gb1, gw2, gb2) = trainfn(x, self.parameters.w1, self.parameters.b1, self.parameters.w2, self.parameters.b2)
+#        return y
+
+    def update(self, instances):
         """
         Update the L{Model} using one training instance.
-        @param instance: A dict from feature index to (non-zero) value.
+        @param instances: A list of dict from feature index to (non-zero) value.
         @todo: Should assert that nonzero_indices and zero_indices
         are correct (i.e. are truly nonzero/zero).
         """
-        x = numpy.zeros(globals.INPUT_DIMENSION)
-        for idx in instance.keys():
-            x[idx] = instance[idx]
+        minibatch = len(instances)
+#        x = pylearn.sparse_instance.to_vector(instances, self.input_dimension)
+        x = pylearn.sparse_instance.to_vector(instances, globals.INPUT_DIMENSION)
 
         (y, h, loss, gw1, gb1, gw2, gb2) = trainfn(x, self.parameters.w1, self.parameters.b1, self.parameters.w2, self.parameters.b2)
 #        print