about summary refs log tree commit diff
path: root/sourcecodes/bnt-master/netlab3.3/demhint.m
diff options
context:
space:
mode:
authorziejd22017-09-28 15:04:40 -0500
committerziejd22017-09-28 15:04:40 -0500
commit8070dc963753142bb86c4ed698d91fd623ed28e7 (patch)
treed0f6dd8fc46a49b819aa55c1a90faa14d8448883 /sourcecodes/bnt-master/netlab3.3/demhint.m
parent7cc31810d53176e805532b2789955f4eedbce6bb (diff)
downloadBNW-8070dc963753142bb86c4ed698d91fd623ed28e7.tar.gz
BNW using Octave instead of Matlab.
This version of BNW should perform the same as the original version. The only difference is that it uses Octave instead of Matlab when running BayesNet Toolbox during parameter learning.

I am calling this BNW_1.02. It can be accessed at:
compbio.uthsc.edu/BNW_1.02
Diffstat (limited to 'sourcecodes/bnt-master/netlab3.3/demhint.m')
-rw-r--r--sourcecodes/bnt-master/netlab3.3/demhint.m49
1 files changed, 49 insertions, 0 deletions
diff --git a/sourcecodes/bnt-master/netlab3.3/demhint.m b/sourcecodes/bnt-master/netlab3.3/demhint.m
new file mode 100644
index 00000000..bd2e5025
--- /dev/null
+++ b/sourcecodes/bnt-master/netlab3.3/demhint.m
@@ -0,0 +1,49 @@
+function demhint(nin, nhidden, nout)
+%DEMHINT Demonstration of Hinton diagram for 2-layer feed-forward network.
+%
+%	Description
+%
+%	DEMHINT plots a Hinton diagram for a 2-layer feedforward network with
+%	5 inputs, 4 hidden units and 3 outputs. The weight vector is chosen
+%	from a Gaussian distribution as described under MLP.
+%
+%	DEMHINT(NIN, NHIDDEN, NOUT) allows the user to specify the number of
+%	inputs, hidden units and outputs.
+%
+%	See also
+%	HINTON, HINTMAT, MLP, MLPPAK, MLPUNPAK
+%
+
+%	Copyright (c) Ian T Nabney (1996-2001)
+
+if nargin < 1 nin = 5; end
+if nargin < 2 nhidden = 7; end
+if nargin < 3 nout = 3; end
+
+% Fix the seed for reproducible results
+randn('state', 42);
+clc
+disp('This demonstration illustrates the plotting of Hinton diagrams')
+disp('for Multi-Layer Perceptron networks.')
+disp(' ')
+disp('Press any key to continue.')
+pause
+net = mlp(nin, nhidden, nout, 'linear');
+
+[h1, h2] = mlphint(net);
+clc
+disp('The MLP has been created with')
+disp(['    ' int2str(nin) ' inputs'])
+disp(['    ' int2str(nhidden) ' hidden units'])
+disp(['    ' int2str(nout) ' outputs'])
+disp(' ')
+disp('One figure is produced for each layer of weights.')
+disp('For each layer the fan-in weights are arranged in rows for each unit.')
+disp('The bias weight is separated from the rest by a red vertical line.')
+disp('The area of each box is proportional to the weight value: positive')
+disp('values are white, and negative are black.')
+disp(' ')
+disp('Press any key to exit.'); 
+pause; 
+delete(h1);
+delete(h2);