private static void ReportPerf(StreamWriter writer, List <DigitImage> data, int epoch, string whichPerformance)
{
var confusionMatrix = new Matrix(layerSizes[L + 1], layerSizes[L + 1]);
double accuracy = 0;
for (int k = 0; k < data.Count; k++)
{
var loss_bak = (double[])Loss.Clone();
Select(data, k);
Forward();
var maxPred = MatrixMath.Max(A[L + 1]);
var label = (int)data[k].label;
confusionMatrix[label, maxPred.Item1]++;
}
accuracy = MatrixMath.Trace(confusionMatrix) / data.Count;
writer.WriteLine(whichPerformance + " Performance at Epoch: " + epoch);
writer.WriteLine(whichPerformance + " Confusion Matrix: ");
writer.WriteLine(confusionMatrix);
writer.WriteLine(whichPerformance + " Accuracy: " + accuracy);
}
private static void Backward(int k)
{
errors[L + 1] = MatrixMath.Subtract(A[L + 1], label); //error at output layer neurons
for (int l = L; l >= 1; l--) // error at hidden layers neurons e[l] = W[l].Transpose * e[l+1]) . F'(Z[l]) where * is matrix multiplication and . is hadamard multiplication
{
errors[l] = MatrixMath.HadamardProduct(MatrixMath.Multiply(MatrixMath.Transpose(W[l]), errors[l + 1]), MatrixMath.F(Z[l], layerFunctions[l], epsilonLeaky, true));
}
for (int l = 0; l <= L; l++)
{
dW[l] = MatrixMath.Multiply(errors[l + 1], MatrixMath.Transpose(A[l]));
db[l] = errors[l + 1];
}
for (int l = 0; l <= L; l++)
{
acc_dW[k][l] = dW[l].Clone();
acc_db[k][l] = db[l].Clone();
//deltaW[l] = MatrixMath.Add(deltaW[l], dW[l]);
//deltab[l] = MatrixMath.Add(deltab[l], db[l]);
}
}
private static void Forward()
{
for (int l = 0; l < L; l++)
{
Z[l + 1] = MatrixMath.Add(MatrixMath.Multiply(W[l], A[l]), b[l]);
A[l + 1] = MatrixMath.F(Z[l + 1], layerFunctions[l + 1], epsilonLeaky, false); //false mean apply function, true means apply function derivative
}
Z[L + 1] = MatrixMath.Add(MatrixMath.Multiply(W[L], A[L]), b[L]); //last layer pre-activation
if (criterion == "MSE") //last layer activation
{
A[L + 1] = Z[L + 1].Clone();
}
else if (criterion == "SoftMax")
{
A[L + 1] = new Matrix(10, 1);
double Denom = MatrixMath.SumExp(Z[L + 1]);
for (int c = 0; c < Z[L + 1].Rows; c++)
{
A[L + 1][c, 0] = Math.Exp(Z[L + 1][c, 0]) / Denom;
}
}
}
private static void ReportBatch(StreamWriter writer, int i, int j)
{
writer.WriteLine("=====> Training Loss after Batch " + (j / batchSize + 1) + " on Epoch " + i + ": " + (Loss[i] /= Training.Count));
for (int l = 0; l <= L; l++)
{
writer.WriteLine("\r\nEpoch " + (i + 1) + " Batch " + (j / batchSize + 1) + " Layer " + (l + 1) + " Weights Gradients Norm:" + MatrixMath.PNorm(deltaW[l], 2));
writer.WriteLine("Epoch " + (i + 1) + " Batch " + (j / batchSize + 1) + " Layer " + (l + 1) + " Biases Gradients Norm:" + MatrixMath.PNorm(deltab[l], 2) + "\r\n");
}
}
private static void Update()
{
for (int l = 0; l <= L; l++)
{
deltaW[l] = MatrixMath.Multiply(deltaW[l], 1.0 / batchSize);
deltab[l] = MatrixMath.Multiply(deltab[l], 1.0 / batchSize);
W[l] = MatrixMath.Subtract(W[l], MatrixMath.Multiply(MatrixMath.Add(deltaW[l], MatrixMath.Multiply(W[l], weightDecay)), learningRate));
b[l] = MatrixMath.Subtract(b[l], MatrixMath.Multiply(deltab[l], learningRate));
}
}