161 lines
3.1 KiB
C++
161 lines
3.1 KiB
C++
#include <NeuralNetwork/FeedForward/Network.h>
|
|
#include <NeuralNetwork/Learning/QuickPropagation.h>
|
|
#include <NeuralNetwork/ActivationFunction/HyperbolicTangent.h>
|
|
|
|
#pragma GCC diagnostic push
|
|
#pragma GCC diagnostic ignored "-Weffc++"
|
|
|
|
#include <gtest/gtest.h>
|
|
|
|
#pragma GCC diagnostic pop
|
|
|
|
TEST(QuickPropagation,XOR) {
|
|
NeuralNetwork::FeedForward::Network n(2);
|
|
NeuralNetwork::ActivationFunction::Sigmoid a(-1);
|
|
n.appendLayer(10,a);
|
|
n.appendLayer(1,a);
|
|
|
|
n.randomizeWeights();
|
|
|
|
NeuralNetwork::Learning::QuickPropagation prop(n);
|
|
|
|
for(int i=0;i<400;i++) {
|
|
prop.teach({1,0},{1});
|
|
prop.teach({1,1},{0});
|
|
prop.teach({0,0},{0});
|
|
prop.teach({0,1},{1});
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,1});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,0});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,0});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
}
|
|
|
|
TEST(QuickPropagation,AND) {
|
|
NeuralNetwork::FeedForward::Network n(2);
|
|
NeuralNetwork::ActivationFunction::Sigmoid a(1.0);
|
|
n.appendLayer(2,a);
|
|
n.appendLayer(1,a);
|
|
|
|
n.randomizeWeights();
|
|
|
|
NeuralNetwork::Learning::QuickPropagation prop(n);
|
|
|
|
for(int i=0;i<400;i++) {
|
|
prop.teach({1,1},{1});
|
|
prop.teach({1,0},{0});
|
|
prop.teach({0,0},{0});
|
|
prop.teach({0,1},{0});
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,1});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,0});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,0});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
}
|
|
|
|
TEST(QuickPropagation,NOTAND) {
|
|
NeuralNetwork::FeedForward::Network n(2);
|
|
NeuralNetwork::ActivationFunction::Sigmoid a(-1);
|
|
n.appendLayer(2,a);
|
|
n.appendLayer(1,a);
|
|
|
|
n.randomizeWeights();
|
|
|
|
NeuralNetwork::Learning::QuickPropagation prop(n);
|
|
|
|
for(int i=0;i<10000;i++) {
|
|
prop.teach({1,1},{0});
|
|
prop.teach({0,0},{1});
|
|
prop.teach({0,1},{1});
|
|
prop.teach({1,0},{1});
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,1});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,0});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({0,0});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
}
|
|
TEST(QuickPropagation,NOTANDHyperbolicTangent) {
|
|
NeuralNetwork::FeedForward::Network n(2);
|
|
NeuralNetwork::ActivationFunction::HyperbolicTangent a(1);
|
|
n.appendLayer(2,a);
|
|
n.appendLayer(1,a);
|
|
|
|
n.randomizeWeights();
|
|
|
|
NeuralNetwork::Learning::QuickPropagation prop(n);
|
|
|
|
for(int i=0;i<10000;i++) {
|
|
prop.teach({1,1},{-1});
|
|
prop.teach({-1,0},{1});
|
|
prop.teach({-1,1},{1});
|
|
prop.teach({1,-1},{1});
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,1});
|
|
ASSERT_LT(ret[0], 0.1);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({-1,1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({1,-1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
|
|
{
|
|
std::vector<float> ret =n.computeOutput({-1,-1});
|
|
ASSERT_GT(ret[0], 0.9);
|
|
}
|
|
} |