public WidgetAttribute(string name, double value, WidgetType type, int widgetId)
{
Name = name;
Value = value;
double attWeight = Calculator.Weights[type][name];
WeightStore.AttWeightedAvgAvailable(Value * attWeight, widgetId);
}
private void ValidateTest(double[] outputlayer, int index, ref WeightStore ws)
{
outputlayer = ConvertFromBinaryToDouble(outputlayer);
for (int i = 0; i < valdataSet[index].PrivateKey.Length; i++)
{
if (valdataSet[index].PrivateKey[i] == (int)outputlayer[i])
{
ws.Statistics[i]++;
}
}
}
private void Validate()
{
bool shouldSave = false;
WeightStore ws = new WeightStore()
{
Statistics = new double[32]
};
for (int i = 0; i < valdataSet.Count; i++)
{
//Layer 0
List <NeuralNetwork> hiddenLayer1 = neuralNetwork.FindAll(x => x.LayerNumber == 0);
double[] weightedSum1 = new double[32];
for (int j = 0; j < hiddenLayer1.Count; j++)
{
weightedSum1[j] = perceptron.Execute(hiddenLayer1[j].Weights, valdataSet[i].PublicAddressDouble, hiddenLayer1[j].Bias);
}
for (int k = 0; k < weightedSum1.Length; k++)
{
weightedSum1[k] = activationFunctions.LeakyReLU(weightedSum1[k]);
}
//Layer 1
List <NeuralNetwork> hiddenLayer2 = neuralNetwork.FindAll(x => x.LayerNumber == 1);
double[] weightedSum2 = new double[64];
for (int j = 0; j < hiddenLayer2.Count; j++)
{
weightedSum2[j] = perceptron.Execute(hiddenLayer2[j].Weights, weightedSum1, hiddenLayer2[j].Bias);
}
for (int k = 0; k < weightedSum2.Length; k++)
{
weightedSum2[k] = activationFunctions.LeakyReLU(weightedSum2[k]);
}
//Layer 2
List <NeuralNetwork> hiddenLayer3 = neuralNetwork.FindAll(x => x.LayerNumber == 2);
double[] weightedSum3 = new double[128];
for (int j = 0; j < hiddenLayer3.Count; j++)
{
weightedSum3[j] = perceptron.Execute(hiddenLayer3[j].Weights, weightedSum2, hiddenLayer3[j].Bias);
}
for (int k = 0; k < weightedSum3.Length; k++)
{
weightedSum3[k] = activationFunctions.LeakyReLU(weightedSum3[k]);
}
//Output Layer
List <NeuralNetwork> outputLayer = neuralNetwork.FindAll(x => x.LayerNumber == 3);
double[] weightedSum4 = new double[256];
for (int j = 0; j < outputLayer.Count; j++)
{
weightedSum4[j] = perceptron.Execute(outputLayer[j].Weights, weightedSum3, outputLayer[j].Bias);
}
for (int k = 0; k < weightedSum4.Length; k++)
{
weightedSum4[k] = activationFunctions.BinaryStep(weightedSum4[k]);
}
ValidateTest(weightedSum4, i, ref ws);
}
for (int i = 0; i < ws.Statistics.Length; i++)
{
if (ws.Statistics[i] > 50)
{
shouldSave = true;
if (ws.Statistics[i] > maxStat)
{
maxStat = ws.Statistics[i];
Console.WriteLine(string.Format("Current highest stat is: {0}, Probability: {1}", maxStat, maxStat / valdataSet.Count));
}
}
}
if (shouldSave)
{
//Console.WriteLine(Environment.NewLine);
//SerialiseWeightsAndSaveToDB(ws.Statistics); //Save to DB using entity framework - uncomment to enable - remember to set connection string in WeightsDBContext
}
}
