void calcOutputNet()
{
int i;
int j;
//calculate the outputs of the hidden neurons
//the hidden neurons are tanh
for(i = 0;i<numHidden;i++)
{
hiddenVal[i] = 0.0;
for(j = 0;j<numInputs;j++)
hiddenVal[i] = hiddenVal[i] + (trainInputs[0][j] * weightsIH[j][i]);
hiddenVal[i] = tanh(hiddenVal[i]);
}
//calculate the output of the network
//the output neuron is linear
outPred = 0.0;
//calculate the output of the network
//the output neuron is linear
//outPred = 0.0;
for(i = 0;i<numHidden;i++)
outPred = outPred + hiddenVal[i] * weightsHO[i];
//calculate the error
//errThisPat = outPred - trainOutput[patnum];
}
//****************************************************//
//********** THIS IS THE MAIN PROGRAM **************************
//==============================================================
main ()
{
int i;
int j;
//initiate the weights
initWeights();
//load in the data
initData();
//train the network
for(j = 0;j <= numEpochs;j++)
{
for(i = 0;i<numPatterns;i++)
{
//select a pattern at its squence
patNum =i;
//calculate the current network output
//and error for this pattern
calcNet();
//change network weights
WeightChangesHO();
WeightChangesIH();
}
//display the overall network error
//after each epoch
for(i = 0;i<numPatterns;i++)
{
patNum =i;
calcOverallError();
}
printf("epoch =%d RMSError =%d\n " ,j, RMSerror);
}
//training has finished
//display the results
displayResults();
// trainInputs[0][0] = 1;
// trainInputs[0][1] = 1;
//trainInputs[0][2] = 1;//bias
//trainInputs[0][3] = 1;
//trainInputs[0][4] = 1;
//trainInputs[0][5] = 1;
// calcOutputNet();
trainInputs[0][0] = 1;
trainInputs[0][1] = 1;
trainInputs[0][2] = 1;//bias
trainInputs[0][3] = 1;
trainInputs[0][4] = 1;
trainInputs[0][5] = 1;
trainInputs[0][6] = 1;
trainInputs[0][7] = 1;
trainInputs[0][8] = 1;
trainInputs[0][9] = 1;
trainInputs[0][10] = -1;
trainInputs[0][11] = -1;
calcOutputNet();
}
//=============================================================
//********** END OF THE MAIN PROGRAM *********************
