# HG changeset patch
# User James Bergstra <bergstrj@iro.umontreal.ca>
# Date 1282673573 14400
# Node ID d68828c98c3863020e22d0061dba0aa372971ee0
# Parent  e70e7446417055a110f047f9f95e9d831bf6a9d8
mcRBM - cleaned up expected hidden unit function

diff -r e70e74464170 -r d68828c98c38 pylearn/algorithms/mcRBM.py
--- a/pylearn/algorithms/mcRBM.py	Tue Aug 24 14:08:24 2010 -0400
+++ b/pylearn/algorithms/mcRBM.py	Tue Aug 24 14:12:53 2010 -0400
@@ -293,24 +293,15 @@
     rval = theano.tensor.grad(cost, list(rbm))
     return rval
 
-def expected_h_g_given_v(P, U, W, b, c, v):
-    """Returns theano expression conditional expectations (`h`, `g`) in an mcRBM.
-    
-    An mcRBM is parametrized
-    by `U`, `W`, `b`, `c`.
-    See module - level documentation for explanations of the `U`, `W`, `b` and `c` parameters.
-
+def expected_h_g_given_v(rbm, v):
+    """Returns tuple (`h`, `g`) of theano expression conditional expectations in an mcRBM.
 
-    The conditional E[h, g | v] is what we need to classify images.
+    `h` is the conditional on the covariance units.
+    `g` is the conditional on the mean units.
+    
     """
-    raise NotImplementedError()
-
-    #TODO: check to see if these args should be negated?
-
-    if P is None:
-        h = nnet.sigmoid(b + 0.5 * cosines(v,U))
-    else:
-        h = nnet.sigmoid(b + 0.5 * dot(cosines(v,U), P))
+    (U, W, a, b, c) = rbm
+    h = TT.nnet.sigmoid(hidden_cov_units_preactivation_given_v(rbm, v))
     g = nnet.sigmoid(c + dot(v,W))
     return (h, g)