--- a/pylearn/algorithms/mcRBM.py	Mon Aug 23 15:54:54 2010 -0400
+++ b/pylearn/algorithms/mcRBM.py	Mon Aug 23 15:59:21 2010 -0400
@@ -40,6 +40,8 @@
         - \sum_j \sum_i W_{ij} g_j v_i
         - \sum_j c_j g_j
 
+For the energy function to correspond to a probability distribution, P must be non-positive.
+
 
 Conventions in this file
 ========================
@@ -70,6 +72,16 @@
 # Recall: 
 #   Q(x) = exp(-E(x))/Z ==> -log(Q(x)) - log(Z) = E(x)
 #
+#
+#   E (v, h, g) =
+#       - 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / |U_{*f}|^2 |v|^2
+#       - \sum_k b_k h_k
+#       + 0.5 \sum_i v_i^2
+#       - \sum_j \sum_i W_{ij} g_j v_i
+#       - \sum_j c_j g_j
+#       - \sum_i a_i v_i
+#
+#
 # Derivation, in which partition functions are ignored.
 #
 # E(v) = -\log(Q(v))
@@ -80,14 +92,20 @@
 #       - \sum_k b_k h_k
 #       + 0.5 \sum_i v_i^2
 #       - \sum_j \sum_i W_{ij} g_j v_i
-#       - \sum_j c_j g_j ))
+#       - \sum_j c_j g_j 
+#       - \sum_i a_i v_i ))
+#
+# Get rid of double negs  in exp
 #  = -\log(  \sum_{h} exp(
 #       + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (|U_{*f}| * |v|)
 #       + \sum_k b_k h_k
 #       - 0.5 \sum_i v_i^2
 #       ) * \sum_{g} exp(
 #       + \sum_j \sum_i W_{ij} g_j v_i
-#       + \sum_j c_j g_j )))
+#       + \sum_j c_j g_j))
+#    - \sum_i a_i v_i 
+#
+# Break up log
 #  = -\log(  \sum_{h} exp(
 #       + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (|U_{*f}|*|v|)
 #       + \sum_k b_k h_k
@@ -96,15 +114,28 @@
 #       + \sum_j \sum_i W_{ij} g_j v_i
 #       + \sum_j c_j g_j )))
 #    + 0.5 \sum_i v_i^2
+#    - \sum_i a_i v_i 
+#
+# Use domain h is binary to turn log(sum(exp(sum...))) into sum(log(..
 #  = -\log(\sum_{h} exp(
 #       + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (|U_{*f}|* |v|)
 #       + \sum_k b_k h_k
 #       ))
 #    - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
 #    + 0.5 \sum_i v_i^2
-#  = - \sum_{k} \log(1 + exp(b_k + 0.5 \sum_f P_{fk}( \sum_i U_{if} v_i )^2 / (|U_{*f}|* #  |v|)))
+#    - \sum_i a_i v_i 
+#
+#  = - \sum_{k} \log(1 + exp(b_k + 0.5 \sum_f P_{fk}( \sum_i U_{if} v_i )^2 / (|U_{*f}|*|v|)))
 #    - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
 #    + 0.5 \sum_i v_i^2
+#    - \sum_i a_i v_i 
+#
+# For negative-one-diagonal P this gives:
+#
+#  = - \sum_{k} \log(1 + exp(b_k - 0.5 \sum_i (U_{ik} v_i )^2 / (|U_{*k}|*|v|)))
+#    - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
+#    + 0.5 \sum_i v_i^2
+#    - \sum_i a_i v_i 
 
 import sys
 import logging