# HG changeset patch
# User Jordi Gutiérrez Hermoso <jordigh@octave.org>
# Date 1321039829 18000
# Node ID 8e8089d5a55b38f7dd43191499c8f7253d0a8fdb
# Parent  55430128adcdf2936e686b0f0e584085592f4b27
Implement randInitializeWeights

diff --git a/randInitializeWeights.m b/randInitializeWeights.m
--- a/randInitializeWeights.m
+++ b/randInitializeWeights.m
@@ -1,32 +1,16 @@
 function W = randInitializeWeights(L_in, L_out)
-%RANDINITIALIZEWEIGHTS Randomly initialize the weights of a layer with L_in
-%incoming connections and L_out outgoing connections
-%   W = RANDINITIALIZEWEIGHTS(L_in, L_out) randomly initializes the weights 
-%   of a layer with L_in incoming connections and L_out outgoing 
-%   connections. 
-%
-%   Note that W should be set to a matrix of size(L_out, 1 + L_in) as
-%   the first row of W handles the "bias" terms
-%
-
-% You need to return the following variables correctly 
-W = zeros(L_out, 1 + L_in);
+  ##RANDINITIALIZEWEIGHTS Randomly initialize the weights of a layer with L_in
+  ##incoming connections and L_out outgoing connections
+  ##   W = RANDINITIALIZEWEIGHTS(L_in, L_out) randomly initializes the weights 
+  ##   of a layer with L_in incoming connections and L_out outgoing 
+  ##   connections. 
+  ##
+  ##   Note that W should be set to a matrix of size(L_out, 1 + L_in) as
+  ##   the first row of W handles the "bias" terms
+  ##
 
-% ====================== YOUR CODE HERE ======================
-% Instructions: Initialize W randomly so that we break the symmetry while
-%               training the neural network.
-%
-% Note: The first row of W corresponds to the parameters for the bias units
-%
-
-
+  ## Randomly initialize the weights to small values
+  epsilon init = 0.12;
+  W = rand(L out, 1 + L in) * 2 * epsilon init − epsilon init;
 
-
-
-
-
-
-
-% =========================================================================
-
-end
+endfunction