Backpropagation UNSUPERVISED null pointer exception

Hello everyone!!!

I was wondering if you could help me with an error that I'm getting.

I'm trying to make a Neural Network with UNSUPERVISED Backpropagation Training method but I don't know how to create the TrainignSet without IDEAL data. When I put NULL in the IDEAL place, I get a null pointer exception in train.iteration();

Mi input set just have one input data and I expect one for output.

Please, Can you give me a simple example to use Backpropagation UNSUPERVISED??

Thanks in advance for all.


public static double MI_INPUT[][]= new double[10][1];
MI_INPUT[0][0] = 0.23;
MI_INPUT[1][0] = 0.027;
MI_INPUT[2][0] = 0.30;
MI_INPUT[3][0] = 0.001;
.
.
.
MLDataSet trainingSet = new BasicMLDataSet(MI_INPUT,null);
network.addLayer(new BasicLayer(null, true, 1));
network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 20));
network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.getStructure().finalizeStructure();
network.setBiasActivation(1.0);
network.reset();
// train the neural network
final Backpropagation train = new Backpropagation(network, trainingSet);
train.fixFlatSpot(false);
int epoch = 1;
do {
train.iteration();
System.out.println("Epoch #" + epoch + " Error:" + train.getError());
epoch++;
} while (train.getError() > 0.005 && epoch <= 600);