Question

There is my implementation of BP alhorithm. I tested it and found incorrect data after training. So, where did I make mistake?

double OpenNNL::_changeWeightsByBP(double * trainingInputs, double *trainingOutputs, double speed, double sample_weight)
{
    double * localGradients = new double[_neuronsCount];
    double * outputs = new double[_neuronsCount];
    double * derivatives = new double[_neuronsCount];

    calculateNeuronsOutputsAndDerivatives(trainingInputs, outputs, derivatives);

    for(int j=0;j<_neuronsPerLayerCount[_layersCount-1];j++)
    {
        localGradients[indexByLayerAndNeuron(_layersCount-1, j)] = trainingOutputs[j] - outputs[indexByLayerAndNeuron(_layersCount-1, j)];
    }

    if(_layersCount > 1)
    {
        for(int i=_layersCount-2;i>=0;i--)
        {
            for(int j=0;j<_neuronsPerLayerCount[i];j++)
            {
                localGradients[indexByLayerAndNeuron(i, j)] = 0;

                for(int k=0;k<_neuronsPerLayerCount[i+1];k++)
                {
                    localGradients[indexByLayerAndNeuron(i, j)] += _neuronsInputsWeights[indexByLayerNeuronAndInput(i+1, k, j)]
                                                                    * localGradients[indexByLayerAndNeuron(i+1, k)];
                }
            }
        }
    }

    for(int j=0;j<_neuronsPerLayerCount[0];j++)
    {
        for(int k=0;k<_inputsCount;k++)
        {
            _neuronsInputsWeights[indexByLayerNeuronAndInput(0, j, k)] += speed * localGradients[indexByLayerAndNeuron(0, j)]
                    * derivatives[indexByLayerAndNeuron(0, j)] * trainingInputs[k];
        }
    }

    for(int i=1;i<_layersCount;i++)
    {
        for(int j=0;j<_neuronsPerLayerCount[i];j++)
        {
            for(int k=0;k<_neuronsPerLayerCount[i-1];k++)
            {
                _neuronsInputsWeights[indexByLayerNeuronAndInput(i, j, k)] += speed * localGradients[indexByLayerAndNeuron(i, j)]
                        * derivatives[indexByLayerAndNeuron(i, j)] * outputs[indexByLayerAndNeuron(i, j)];
            }
        }
    }

    delete[] localGradients;
    delete[] outputs;
    delete[] derivatives;
}

And how to compute error of network’s output for stopping training process?

And how to change neurons’ biases?

There is my full code: https://github.com/NicholasShatokhin/OpenNNL if you need it.

Answer 1

I found problem. Instead of outputs[indexByLayerAndNeuron(i, j)] in last cycle I must write outputs[indexByLayerAndNeuron(i-1, k)].