MATLAB: Does the block created from a NEWPNN network using the GENSIM function give unexpected results

Deep Learning Toolboxgensimnetworksneuralnewpnnresultsimgensimulinksparseunexpected

I have created and trained a neural network using the NEWPNN function, and the output in MATLAB is correct. However, when I use GENSIM to create a block from this network, the output in Simulink does not appear to be correct. The output of the block is all ones.

Best Answer

This bug has been fixed in Release 14 Service Pack 3 (R14SP3). For previous product releases, read below for any possible workarounds:

The problem is that the data generated by your NEWPNN network is a sparse matrix. You can verify this by simulating your network using the same data with which you constructed it. MATLAB and Simulink handle sparse matrices differently. Therefore, you are not seeing the same results in Simulink.

Related Solutions

MATLAB: How to compile MATLAB files that call Neural Network Toolbox functions into stand-alone applications, in MATLAB releases R13 or older

Compiler releases before 3.0 (R13) do not support deployment of MATLAB objects within functions; the Neural Network Toolbox therefore does not allow you to export a trained network to C, C++, or Java for these releases.

If you are trying to use a trained network in a C or Java environment you can use the following steps:

1) Train the network 'completely' in the Neural Network Toolbox.

2) Use the GENSIM function to create a Simulink block of the trained network.

3) Use the Real Time Workshop to create a standalone application.

Alternately, you can save the weight matrix and bias matrix along with other information about the network into a data file and read it into your C, C++, or Java application.

Here is an example that demonstrates this:

P = [0 1 2 3 4 5 6 7 8 9 10];
T = [0 1 2 3 4 3 2 1 2 3 4];
% Before training, use the following code
net = newff([0 10],[5 1],{'tansig' 'purelin'});
Y = sim(net,P);
plot(P,T,P,Y,'o')

Now, train the system using the following code:

net.trainParam.epochs = 50;
net = train(net,P,T);
Y = sim(net,P);
plot(P,T,P,Y,'o')
%%Using GENSIM
gensim(net)

Then the input and output are replaced by the From File and To File block. The From File reads from the newfrom.mat file that is created using the following:

t=[0:10];
u=ones(1,11);
tu=[t;u];
save newfrom.mat tu;

Suppose we want to tune only the following weight:

my_neuralnet/Neural Network/Layer 1/IW{1,1}/IW{1,1}(1,:)'

So we go to this Constant block and change the value to a symbolic value, say "Pooh". Then we need to inline parameters and configure Pooh as a tunable parameter. Then we need to build the model. To change Pooh to 100, you can simply use the following:

pooh = 100;
myrtp = rsimgetrtp('my_neuralnet');
save myparamfile myrtp;
!my_neuralnet -p myparamfile.mat

MATLAB: Please help me to implement math lab code for classification of cytological images using probabilistic neural network???math lab code for testing image using PNN???/

1. Read the help and doc documentation and try the documentation examples

>> lookfor PNN

newpnn - Design a probabilistic neural network.

demopnn1 - PNN Classification

>> help newpnn

>> doc newpnn

>> help demopnn1

>> doc demopnn1

2. Apply the code to other NN example data sets

>> help nndatasets

>> doc nndatasets

3. Search for newpnn posts in the NEWGROUP and ANSWERS

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: How to compile MATLAB files that call Neural Network Toolbox functions into stand-alone applications, in MATLAB releases R13 or older

MATLAB: Please help me to implement math lab code for classification of cytological images using probabilistic neural network???math lab code for testing image using PNN???/

Related Question