Relintai/MLPP
1
0
Fork 0
mirror of https://github.com/Relintai/MLPP.git synced 2024-11-12 10:15:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

"Vectorized" sigmoid

Browse Source
This commit is contained in:
novak_99 2021-05-26 00:19:26 -07:00
parent db8283212d
commit 558e138948
3 changed files with 18 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
MLPP/Activation/Activation.cpp
View File

@ -38,33 +38,15 @@ namespace MLPP{
}
std::vector<double> Activation::sigmoid(std::vector<double> z, bool deriv){
if(deriv) {
LinAlg alg;
return alg.subtraction(sigmoid(z), alg.hadamard_product(sigmoid(z), sigmoid(z)));
}
std::vector<double> a;
a.resize(z.size());
for(int i = 0; i < z.size(); i++){
a[i] = sigmoid(z[i]);
}
return a;
LinAlg alg;
if(deriv) { return alg.subtraction(sigmoid(z), alg.hadamard_product(sigmoid(z), sigmoid(z))); }
return alg.elementWiseDivision(alg.onevec(z.size()), alg.addition(alg.onevec(z.size()), alg.exp(alg.scalarMultiply(-1, z))));
}
std::vector<std::vector<double>> Activation::sigmoid(std::vector<std::vector<double>> z, bool deriv){
if(deriv) {
LinAlg alg;
return alg.subtraction(sigmoid(z), alg.hadamard_product(sigmoid(z), sigmoid(z)));
}
std::vector<std::vector<double>> a;
a.resize(z.size());
for(int i = 0; i < z.size(); i++){
a[i] = sigmoid(z[i]);
}
return a;
LinAlg alg;
if(deriv) { return alg.subtraction(sigmoid(z), alg.hadamard_product(sigmoid(z), sigmoid(z))); }
return alg.elementWiseDivision(alg.onemat(z.size(), z[0].size()), alg.addition(alg.onemat(z.size(), z[0].size()), alg.exp(alg.scalarMultiply(-1, z))));
}
std::vector<double> Activation::softmax(std::vector<double> z){

BIN
a.out
View File

Binary file not shown.

23
main.cpp
View File

@ -231,7 +231,7 @@ int main() {
// ANN ann(alg.transpose(inputSet), outputSet);
// ann.addLayer(10, "RELU", "Default", "Ridge", 0.0001);
// ann.addLayer(10, "Sigmoid", "Default");
// ann.addOutputLayer("Softplus", "LogLoss", "XavierNormal");
// ann.addOutputLayer("Sigmoid", "LogLoss", "XavierNormal");
// ann.gradientDescent(0.1, 80000, 0);
// alg.printVector(ann.modelSetTest(alg.transpose(inputSet)));
// std::cout << "ACCURACY: " << 100 * ann.score() << "%" << std::endl;
@ -348,18 +348,19 @@ int main() {
// OutlierFinder outlierFinder(2); // Any datapoint outside of 2 stds from the mean is marked as an outlier.
// alg.printVector(outlierFinder.modelTest(inputSet));
// Testing for new Functions
double z_s = 4;
std::cout << avn.sinh(z_s) << std::endl;
std::cout << avn.sinh(z_s, 1) << std::endl;
// // Testing for new Functions
// double z_s = 4;
// std::cout << avn.sigmoid(z_s) << std::endl;
// std::cout << avn.sigmoid(z_s, 1) << std::endl;
std::vector<double> z_v = {4, 5};
alg.printVector(avn.sinh(z_v));
alg.printVector(avn.sinh(z_v, 1));
// std::vector<double> z_v = {4, 5};
// alg.printVector(avn.sigmoid(z_v));
// alg.printVector(avn.sigmoid(z_v, 1));
// std::vector<std::vector<double>> Z_m = {{4, 5}};
// alg.printMatrix(avn.sigmoid(Z_m));
// alg.printMatrix(avn.sigmoid(Z_m, 1));
std::vector<std::vector<double>> Z_m = {{4, 5}};
alg.printMatrix(avn.sinh(Z_m));
alg.printMatrix(avn.sinh(Z_m, 1));
// alg.printMatrix(alg.pinverse({{1,2}, {3,4}}));