public void ShouldProduceActivation()
{
_activationFunction.Activate(Arg.Is <double>(x => x == 21)).Returns(1);
_activationFunction.Activate(Arg.Is <double>(x => x == 26)).Returns(5);
_activationFunction.Activate(Arg.Is <double>(x => x == 31)).Returns(3);
var fullyConnectedLayer = new FullyConnectedLayer(_activationFunction, new double[] { 1, 2, 3, 3, 2, 1, 1, 2, 3 }, new double[] { 1, 2, 3 });
fullyConnectedLayer.Produce(new double[] { 3, 4, 5 });
fullyConnectedLayer.Activations.Should().NotBeNull();
fullyConnectedLayer.Activations.Should().ContainInOrder(new double[] { 1, 5, 3 });
_activationFunction.Received(3).Activate(Arg.Any <double>());
}
public void Update()
{
var dotProduct = Inputs.Select(kvp => kvp.Value)
.Sum(synapse => synapse.Input.GetValue()*synapse.Weight);
double output = _activationFunction.Activate(dotProduct);
_cachedOutput = output;
}
public void FeedForward(Layer prevLayer)
{
float sum = 0f;
foreach (var neuron in prevLayer)
{
float val = neuron.GetOutputValue();
float weight = neuron._outputWeights[_myIndex];
sum += val * weight;
}
_output = _transfer.Activate(sum);
}
public double Activate(double[] inputSignals)
{
if (inputSignals.Length != Weights.Length)
{
throw new Exception("Neuron weights number must be the same as input signals number passed to it");
}
OutputSignal = default(double);
for (var i = 0; i < inputSignals.Length; i++)
{
InputSignals[i] = inputSignals[i];
OutputSignal += inputSignals[i] * Weights[i];
}
return(_activationFunction.Activate(OutputSignal));
}
public double Output()
{
return(transferFunc.Activate(NetValue));
}
public void FeedForward(Array <float> feed)
{
_target.SumVector = NumMath.SumColumn(feed.H * _target.KnowlodgeMatrix) + _target.BiasVector;
_target.OutputVector = _activationFunction.Activate(_target.SumVector);
}
public virtual void Activate()
{
_target.OutputVector = _activationFunction.Activate(_target.SumVector);
}