int main(int argc, char *argv[])
{
testSequence();
testUnivariateStats();
testBivariateStats();
testUtility();
testVectorAlgebra();
testMatrixDeterminant();
testMatrixInverse();
testLUFactorisation();
testLUSolver();
testGaussianElimination();
testInterpolation();
testIntegration();
testRoot();
testTimeStep();
testRSignificanceTest();
testChiSquared();
testMultipleRegression();
test_golden_fit();
testSimplex();
testSimplex2();
testSimplex3();
test_simplex_fit();
return (EXIT_SUCCESS);
}
int main()
{
testSequence2();
return 0;
testSequenceCMAES();
return 0;
testSequence();
return 0;
testLogs();
return 0;
//Plot real target function
Leph::Plot plot;
for (double x=0.0;x<=1.0;x+=0.03) {
for (double y=0.0;y<=1.0;y+=0.03) {
plot.add(Leph::VectorLabel(
"x", x,
"y", y,
"real", function(x, y)));
}
}
//Initialize Gaussian Process
libgp::GaussianProcess gp(2, "CovSum ( CovSEiso, CovNoise)");
//Adding noised data point to model
for (size_t k=0;k<100;k++) {
double x = 0.5*uniform(generator) + 0.5;
double y = 0.5*uniform(generator) + 0.5;
double f = function(x, y) + noise(1.0);
plot.add(Leph::VectorLabel(
"x", x,
"y", y,
"target", f));
double input[] = {x, y};
gp.add_pattern(input, f);
}
//Optimize hyper parameter
libgp::RProp rprop;
rprop.init();
rprop.maximize(&gp, 50, true);
//Predict fitted model
for (double x=0.0;x<=1.0;x+=0.04) {
for (double y=0.0;y<=1.0;y+=0.04) {
double input[] = {x, y};
plot.add(Leph::VectorLabel(
"x", x,
"y", y,
"fitted", gp.f(input)));
}
}
//Display plot
plot.plot("x", "y", "all").render();
return 0;
}
int main(int argc, char** argv) {
int period;
int sequence[4] = {1, 2, 0, 3}; // cf. Table 1
period = sizeof(sequence) / sizeof(sequence[0]);
testSequence(period, 0, sequence);
return 0;
}
int main()
{
const int repeats = 8;
const int steps = 350;
const size_t kb = 1024;
const size_t mb = 1024 * kb;
size_t init_size = 16 * kb / sizeof(Node);
size_t small_init_size = 1 * kb / sizeof(Node);
size_t size = 1 * kb / sizeof(Node);
Node * nodes = initNodeArray(size);
for(int j = 0; j < steps; j++) {
double rand_sum = 0;
double seq_sum = 0;
for(int i = 0; i < repeats; i++) {
nodes = initNodeArray(size);
seq_sum += testSequence(nodes, size);
rand_sum += testRandom(nodes, size);
}
std::cout.setf(std::ios::fixed);
std::cout.precision( 3 );
std::cout << size / sizeof(Node) << "kb :"
<< seq_sum * 1000 /(size * (double)repeats) << " --- "
<< rand_sum * 1000 /(size * (double)repeats)
<< std::endl;
if(size >= init_size * 3)
size += init_size;
else
size += small_init_size;
}
delete[] nodes;
return 0;
}
main(int argc, char *argv[], char *envp[])
{
testSequence();
}
void SkaarhojUHB::testSequence() { testSequence(20); }
void SkaarhojBroadcastButtons::testSequence() { testSequence(20); }
