mandlm
/
Neuro
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Working net, calculates the mean value of two inputs

main
mandlm 2015-10-23 22:16:12 +02:00
parent 6ed30e56c4
commit 4eb232b1e9
2 changed files with 28 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Layer.cpp
View File

@ -46,13 +46,13 @@ void Layer::connectTo(const Layer & nextLayer)
{ {
for (Neuron &neuron : *this) for (Neuron &neuron : *this)
{ {
neuron.createOutputWeights(nextLayer.sizeWithoutBiasNeuron(), 0.5); neuron.createOutputWeights(nextLayer.sizeWithoutBiasNeuron(), 1.0);
} }
} }
void Layer::updateInputWeights(Layer & prevLayer) void Layer::updateInputWeights(Layer & prevLayer)
{ {
static const double trainingRate = 0.2; static const double trainingRate = 0.3;
for (size_t targetLayerIndex = 0; targetLayerIndex < sizeWithoutBiasNeuron(); ++targetLayerIndex) for (size_t targetLayerIndex = 0; targetLayerIndex < sizeWithoutBiasNeuron(); ++targetLayerIndex)
{ {

31
Neuro.cpp
View File

@ -2,8 +2,12 @@
#include <exception> #include <exception>
#include <algorithm> #include <algorithm>
#include <assert.h>
#include "Net.h" #include "Net.h"
const double pi = std::acos(-1);
int main() int main()
{ {
try try
@ -12,7 +16,12 @@ int main()
Net myNet({ 2, 3, 1 }); Net myNet({ 2, 3, 1 });
size_t numIterations = 10000; size_t batchSize = 5000;
size_t batchIndex = 0;
double batchMaxError = 0.0;
double batchMeanError = 0.0;
size_t numIterations = 1000000;
for (size_t iteration = 0; iteration < numIterations; ++iteration) for (size_t iteration = 0; iteration < numIterations; ++iteration)
{ {
std::vector<double> inputValues = std::vector<double> inputValues =
@ -23,7 +32,7 @@ int main()
std::vector<double> targetValues = std::vector<double> targetValues =
{ {
*std::max_element(inputValues.begin(), inputValues.end()) (inputValues[0] + inputValues[1]) / 2.0
}; };
myNet.feedForward(inputValues); myNet.feedForward(inputValues);
@ -32,9 +41,21 @@ int main()
double error = outputValues[0] - targetValues[0]; double error = outputValues[0] - targetValues[0];
std::cout << "Error: "; batchMeanError += error;
std::cout << std::abs(error); batchMaxError = std::max<double>(batchMaxError, error);
std::cout << std::endl;
if (batchIndex++ == batchSize)
{
std::cout << "Batch error (" << batchSize << " iterations, max/mean): ";
std::cout << std::abs(batchMaxError);
std::cout << " / ";
std::cout << std::abs(batchMeanError / batchSize);
std::cout << std::endl;
batchIndex = 0;
batchMaxError = 0.0;
batchMeanError = 0.0;
}
myNet.backProp(targetValues); myNet.backProp(targetValues);
} }