Perceptron Model in C++ not Converging - c++

Question

So I was writing a simple Perceptron model and when I finished the code and saw that there were no errors I was pretty surprised. But it seems like my model doesn't converge (along with some other oddities).
Basically it keeps getting 25/100 samples right at every epoch. And when every epoch ends the weights are always coming back to 0.
Due to the fact that the code is on multiple files I put it on Google Drive here it is:
https://drive.google.com/folderview?id=0B_r3mf9HbUrLaDNlc1F6RXhNMnM&usp=sharing
It is a Visual Studio Community 2013 project. You can open and run it so that you get a better idea.
Here's a quick preview of the files though.
main.cpp:
#include <iostream>
#include <vector>
#include <algorithm>
#include <fstream>
#include <string>
#include <math.h>
#include "LinearAlgebra.h"
#include "MachineLearning.h"
using namespace std;
using namespace LinearAlgebra;
using namespace MachineLearning;
void printVector(vector< vector<float> > X);
vector< vector<float> > getIrisX();
vector<float> getIrisy();
int main()
{
vector< vector<float> > X = getIrisX();
vector<float> y = getIrisy();
vector<float> test1;
test1.push_back(5.0);
test1.push_back(3.3);
test1.push_back(1.4);
test1.push_back(0.2);
vector<float> test2;
test2.push_back(6.0);
test2.push_back(2.2);
test2.push_back(5.0);
test2.push_back(1.5);
//printVector(X);
//for (int i = 0; i < y.size(); i++){ cout << y[i] << " "; }cout << endl;
perceptron clf(0.1, 10);
clf.fit(X, y);
cout << "Now Predicting: 5.0,3.3,1.4,0.2(CorrectClass=1,Iris-setosa) -> " << clf.predict(test1) << endl;
cout << "Now Predicting: 6.0,2.2,5.0,1.5(CorrectClass=-1,Iris-virginica) -> " << clf.predict(test2) << endl;
system("PAUSE");
return 0;
}
void printVector(vector< vector<float> > X)
{
for (int i = 0; i < X.size(); i++)
{
for (int j = 0; j < X[i].size(); j++)
{
cout << X[i][j] << " ";
}
cout << endl;
}
}
vector<float> getIrisy()
{
vector<float> y;
ifstream inFile;
inFile.open("y.data");
string sampleClass;
for (int i = 0; i < 100; i++)
{
inFile >> sampleClass;
if (sampleClass == "Iris-setosa")
{
y.push_back(1);
}
else
{
y.push_back(-1);
}
}
return y;
}
vector< vector<float> > getIrisX()
{
ifstream af;
ifstream bf;
ifstream cf;
ifstream df;
af.open("a.data");
bf.open("b.data");
cf.open("c.data");
df.open("d.data");
vector< vector<float> > X;
for (int i = 0; i < 100; i++)
{
char scrap;
int scrapN;
af >> scrapN;
bf >> scrapN;
cf >> scrapN;
df >> scrapN;
af >> scrap;
bf >> scrap;
cf >> scrap;
df >> scrap;
float a, b, c, d;
af >> a;
bf >> b;
cf >> c;
df >> d;
X.push_back(vector < float > {a, b, c, d});
}
af.close();
bf.close();
cf.close();
df.close();
return X;
}
MachineLearning.h:
#pragma once
#include<vector>
using namespace std;
namespace MachineLearning{
class perceptron
{
public:
perceptron(float eta,int epochs);
float netInput(vector<float> X);
int predict(vector<float> X);
void fit(vector< vector<float> > X, vector<float> y);
private:
float m_eta;
int m_epochs;
vector < float > m_w;
vector < float > m_errors;
};
}
MachineLearning.cpp
#include<vector>
#include <algorithm>
#include <iostream>
#include<fstream>
#include <math.h>
#include "MachineLearning.h"
using namespace std;
namespace MachineLearning{
perceptron::perceptron(float eta, int epochs)
{
m_epochs = epochs;
m_eta = eta;
}
void perceptron::fit(vector< vector<float> > X, vector<float> y)
{
for (int i = 0; i < X[0].size() + 1; i++) // X[0].size() + 1 -> I am using +1 to add the bias term
{
m_w.push_back(0);
}
for (int i = 0; i < m_epochs; i++)
{
int errors = 0;
for (int j = 0; j < X.size(); j++)
{
float update = m_eta * (y[j] - predict(X[j]));
m_w[0] = update;
for (int w = 1; w < m_w.size(); w++){ m_w[w] = update * X[j][w - 1]; }
errors += update != 0 ? 1 : 0;
}
m_errors.push_back(errors);
}
}
float perceptron::netInput(vector<float> X)
{
// Sum(Vector of weights * Input vector) + bias
float probabilities = m_w[0];
for (int i = 0; i < X.size(); i++)
{
probabilities += X[i] * m_w[i + 1];
}
return probabilities;
}
int perceptron::predict(vector<float> X)
{
return netInput(X) > 0 ? 1 : -1; //Step Function
}
}
Any kind of help is much appreciated.
Thanks in advance.
Panos P.

Answer 1

After hours of tedious debugging I finally found the mistake. There was a bug in my code when I updated the weights.
for (int j = 0; j < X.size(); j++)
{
float update = m_eta * (y[j] - predict(X[j]));
m_w[0] = update;
for (int w = 1; w < m_w.size(); w++){ m_w[w] = update * X[j][w - 1]; }
errors += update != 0 ? 1 : 0;
}
notice that:
m_w[w] = update * X[j][w - 1]
I am setting the weights as equal to the update. It looks like I forgot a "+" sign. Now it works fine.
Here's it is now:
m_w[w] += update * X[j][w - 1]
Sometimes the silliest mistakes can cause the most annoying of errors.
I hope that this might help anyone making the same mistake.