public void TestSoftMax()
{
var activation = new ActivationSoftMax();
Assert.IsTrue(activation.HasDerivative);
var clone = activation.Clone();
Assert.IsInstanceOfType(clone, typeof(ActivationSoftMax));
double[] input = { 1, 2, 3 };
activation.ActivationFunction(input, 0, 3);
Assert.AreEqual(0.09, input[0], 0.01);
Assert.AreEqual(0.24, input[1], 0.01);
Assert.AreEqual(0.67, input[2], 0.01);
double sum = input[0] + input[1] + input[2];
Assert.AreEqual(1, sum, EncogFramework.DefaultDoubleEqual);
input[0] = activation.DerivativeFunction(input[0], input[0]);
Assert.AreEqual(1.0, input[0], EncogFramework.DefaultDoubleEqual);
}
public EncogSoftMaxActivation()
: base()
{
activationFunction = new ActivationSoftMax();
activationLevel = 1.0;
activationMin = 0.0;
activationMax = 1.0;
}
void AddLayers(List<LayerConfig> gen)
{
foreach (var g in gen)
{
IActivationFunction act;
if (g.ActivationType == 0)
{
act = new ActivationBiPolar();
}
switch (g.ActivationType )
{
case 0:
act = new ActivationBiPolar();
break;
case 1:
act = new ActivationBipolarSteepenedSigmoid ();
break;
case 2:
act = new ActivationClippedLinear();
break;
case 3:
act = new ActivationCompetitive();
break;
case 4:
act = new ActivationElliott();
break;
case 5:
act = new ActivationElliottSymmetric();
break;
case 6:
act = new ActivationGaussian();
break;
case 7:
act = new ActivationLinear();
break;
case 8:
act = new ActivationLOG();
break;
case 9:
act = new ActivationRamp();
break;
case 10:
act = new ActivationRamp();
break;
case 11:
act = new ActivationSigmoid();
break;
case 12:
act = new ActivationSIN();
break;
case 13:
act = new ActivationSoftMax();
break;
case 14:
act = new ActivationSteepenedSigmoid();
break;
case 15:
act = new ActivationStep();
break;
case 16:
act = new ActivationTANH();
break;
default:
act = new ActivationSoftMax();
break;
}
network.AddLayer(new BasicLayer(act, g.hasBias, g.neurons));
}
}
