sbugrov

// dz2 = dyhat * W3.T * relu'(a2)
vector<float> dz2 = dot(dyhat, transpose( &W3[0], 64, 10 ), BATCH_SIZE, 10, 64) * reluPrime(a2);

sbugrov

// dW2 = a1.T * dz2
vector<float> dW2 = dot(transpose( &a1[0], BATCH_SIZE, 128 ), dz2, 128, BATCH_SIZE, 64);

sbugrov

vector<float> dW3 = dot(transpose( &a2[0], BATCH_SIZE, 64 ), dyhat, 64, BATCH_SIZE, 10);

sbugrov

vector<float> dyhat = yhat - b_y;

sbugrov

vector <float> relu(const vector <float>& z){
    int size = z.size();
    vector <float> output;
    for( int i = 0; i < size; ++i ) {
        if (z[i] < 0){
            output.push_back(0.0);
        }
        else output.push_back(z[i]);
    }
    return output;

sbugrov

// # Feed forward
vector<float> a1 = relu(dot( b_X, W1, BATCH_SIZE, 784, 128 ));
vector<float> a2 = relu(dot( a1, W2, BATCH_SIZE, 128, 64 ));
vector<float> yhat = softmax(dot( a2, W3, BATCH_SIZE, 64, 10 ), 10);

// # Back propagation
vector<float> dyhat = yhat - b_y;
vector<float> dW3 = dot(transpose( &a2[0], BATCH_SIZE, 64 ), dyhat, 64, BATCH_SIZE, 10);
vector<float> dz2 = dot(dyhat, transpose( &W3[0], 64, 10 ), BATCH_SIZE, 10, 64) * reluPrime(a2);
vector<float> dW2 = dot(transpose( &a1[0], BATCH_SIZE, 128 ), dz2, 128, BATCH_SIZE, 64);

sbugrov

./perceptron

sbugrov

nvcc -arch=sm_50 -rdc=true -lcudadevrt onehiddenlayerperceptron.cu -o perceptron

sbugrov

Prediction[0] : 0.060997 True Value[0] : 0.000000 Error[0] : 0.060997
Prediction[1] : 0.076193 True Value[1] : 0.000000 Error[1] : 0.076193
Prediction[2] : 0.927551 True Value[2] : 1.000000 Error[2] : -0.072449
Prediction[3] : 0.918263 True Value[3] : 1.000000 Error[3] : -0.081737

sbugrov

dDot_m1T_m2( X, l_1_d, W0, X_h, X_w, l1_w );