Output of neural network holds same values everytime - c++

Question

I am working on a very simple feed forward neural network to practice my programming skills. There are 3 classes :
Neural::Net ; builds the network, feeds forward input values (no backpropagation for the moment)
Neural::Neuron ; has characteristics of the neuron (index, output, weight etc)
Neural::Connection ; a structure-like class that randomizes the weights and hold the output, delta weight etc..
The program is very basic: I build the network with 2 hidden layers and randomized weights, then ask it to feed forward the same input values.
My problem is: It is expected that the program ends up with different output values after every run, yet the output are always the same. I tried placing markers everywhere to understand why it is calculating the same thing over and over again but I can't put my finger on the error.
Here is the code:
#include <iostream>
#include <cassert>
#include <cstdlib>
#include <vector>
#include "ConsoleColor.hpp"
using namespace std;
namespace Neural {
class Neuron;
typedef vector<Neuron> Layer;
// ******************** Class: Connection ******************** //
class Connection {
public:
Connection();
void setOutput(const double& outputVal) { myOutputVal = outputVal; }
void setWeight(const double& weight) { myDeltaWeight = myWeight - weight; myWeight = weight; }
double getOutput(void) const { return myOutputVal; }
double getWeight(void) const { return myWeight; }
private:
static double randomizeWeight(void) { return rand() / double(RAND_MAX); }
double myOutputVal;
double myWeight;
double myDeltaWeight;
};
Connection::Connection() {
myOutputVal = 0;
myWeight = Connection::randomizeWeight();
myDeltaWeight = myWeight;
cout << "Weight: " << myWeight << endl;
}
// ******************** Class: Neuron ************************ //
class Neuron {
public:
Neuron();
void setIndex(const unsigned int& index) { myIndex = index; }
void setOutput(const double& output) { myConnection.setOutput(output); }
unsigned int getIndex(void) const { return myIndex; }
double getOutput(void) const { return myConnection.getOutput(); }
void feedForward(const Layer& prevLayer);
void printOutput(void) const;
private:
inline static double transfer(const double& weightedSum);
Connection myConnection;
unsigned int myIndex;
};
Neuron::Neuron() : myIndex(0), myConnection() { }
double Neuron::transfer(const double& weightedSum) { return 1 / double((1 + exp(-weightedSum))); }
void Neuron::printOutput(void) const { cout << "Neuron " << myIndex << ':' << myConnection.getOutput() << endl; }
void Neuron::feedForward(const Layer& prevLayer) {
// Weight sum of the previous layer's output values
double weightedSum = 0;
for (unsigned int i = 0; i < prevLayer.size(); ++i) {
weightedSum += prevLayer[i].getOutput()*myConnection.getWeight();
cout << "Neuron " << i << " from prevLayer has output: " << prevLayer[i].getOutput() << endl;
cout << "Weighted sum: " << weightedSum << endl;
}
// Transfer function
myConnection.setOutput(Neuron::transfer(weightedSum));
cout << "Transfer: " << myConnection.getOutput() << endl;
}
// ******************** Class: Net *************************** //
class Net {
public:
Net(const vector<unsigned int>& topology);
void setTarget(const vector<double>& targetVals);
void feedForward(const vector<double>& inputVals);
void backPropagate(void);
void printOutput(void) const;
private:
vector<Layer> myLayers;
vector<double> myTargetVals;
};
Net::Net(const vector<unsigned int>& topology) : myTargetVals() {
assert(topology.size() > 0);
for (unsigned int i = 0; i < topology.size(); ++i) { // Creating the layers
myLayers.push_back(Layer(((i + 1) == topology.size()) ? topology[i] : topology[i] + 1)); // +1 is for bias neuron
// Setting each neurons index inside layer
for (unsigned int j = 0; j < myLayers[i].size(); ++j) {
myLayers[i][j].setIndex(j);
}
// Console log
cout << red;
if (i == 0) {
cout << "Input layer (" << myLayers[i].size() << " neurons including bias neuron) created." << endl;
myLayers[i].back().setOutput(1);
}
else if (i < topology.size() - 1) {
cout << "Hidden layer " << i << " (" << myLayers[i].size() << " neurons including bias neuron) created." << endl;
myLayers[i].back().setOutput(1);
}
else { cout << "Output layer (" << myLayers[i].size() << " neurons) created." << endl; }
cout << white;
}
}
void Net::setTarget(const vector<double>& targetVals) { assert(targetVals.size() == myLayers.back().size()); myTargetVals = targetVals; }
void Net::feedForward(const vector<double>& inputVals) {
assert(myLayers[0].size() - 1 == inputVals.size());
for (unsigned int i = 0; i < inputVals.size(); ++i) { // Setting input vals to input layer
cout << yellow << "Setting input vals...";
myLayers[0][i].setOutput(inputVals[i]); // myLayers[0] is the input layer
cout << "myLayer[0][" << i << "].getOutput()==" << myLayers[0][i].getOutput() << white << endl;
}
for (unsigned int i = 1; i < myLayers.size() - 1; ++i) { // Updating hidden layers
for (unsigned int j = 0; j < myLayers[i].size() - 1; ++j) { // - 1 because bias neurons do not have input
cout << "myLayers[" << i << "].size()==" << myLayers[i].size() << endl;
cout << green << "Updating neuron " << j << " inside layer " << i << white << endl;
myLayers[i][j].feedForward(myLayers[i - 1]); // Updating the neurons output based on the neurons of the previous layer
}
}
for (unsigned int i = 0; i < myLayers.back().size(); ++i) { // Updating output layer
cout << green << "Updating output neuron " << i << ": " << white << endl;
const Layer& prevLayer = myLayers[myLayers.size() - 2];
myLayers.back()[i].feedForward(prevLayer); // Updating the neurons output based on the neurons of the previous layer
}
}
void Net::printOutput(void) const {
for (unsigned int i = 0; i < myLayers.back().size(); ++i) {
cout << blue; myLayers.back()[i].printOutput(); cout << white;
}
}
void Net::backPropagate(void) {
}
}
int main(int argc, char* argv[]) {
vector<unsigned int> myTopology;
myTopology.push_back(3);
myTopology.push_back(4);
myTopology.push_back(2);
myTopology.push_back(2);
cout << myTopology.size() << endl << endl; // myTopology == {3, 4, 2 ,1}
vector<double> myTargetVals= {0.5,1};
vector<double> myInputVals= {1, 0.5, 1};
Neural::Net myNet(myTopology);
myNet.feedForward(myInputVals);
myNet.printOutput();
return 0;
}
Edit: I figured that the bias neuron in the input layer was correctly set to output 1 while the ones in the hidden layers are set to 0 and I fixed that. But the outputs are still the same every run. I did the math on a sheet of paper and it works out. Here is the output (Color coded for clarity) :
I have expected the values to be random just like the weights. Shouldn't that be the case ? I am confused.

Answer 1

I found my mistake. I thought that rand() initialized its seed automatically. I knew it was a dumb thing. I added srand(time(NULL)); at the beginning of the program and now it works as it should.