MLP_cannonball7
Download scriptThis script implements an Artificial Intelligence model known as a Multi-Layer Perceptron (MLP). In simple terms, it is a type of neural network designed to learn and predict outcomes based on specific inputs—in this case, simulating the physics of a projectile (like a cannonball).
The Core Objective
The program aims to solve a regression problem: predicting the horizontal ($x$) and vertical ($y$) positions of a bullet at a specific point in time. It does this by looking at two primary variables:
- Initial Speed
- Launch Angle
Instead of just using a rigid mathematical formula, the script creates an artificial "brain" that learns the relationship between speed, angle, and position through experience and repetition.
How the Logic Works
1. Data Generation (The "Textbook")
The script begins by creating a large dataset of examples. It generates random combinations of speeds and angles, then calculates the correct $x$ and $y$ positions using standard physics equations (considering gravity). This serves as the "answer key" for the AI to study.
2. The Neural Network Structure
The MLP is structured into three main stages:
- Input Layer: Receives multiple data points regarding the bullet's initial conditions.
- Hidden Layer: This acts as the processing center. It contains many "neurons" that take the input data, multiply it by internal weights (importance levels), and pass it through a non-linear function. This allows the AI to understand complex patterns that aren't just simple straight lines.
- Output Layer: Takes the processed information from the hidden layer and produces the final estimates for the $x$ and $y$ coordinates.
3. The Training Process (Learning)
The script uses a method called "Stochastic Gradient Descent" to improve itself. The process follows these steps:
- Forward Pass: The AI takes a set of input data (speed and angle) and makes a guess at where the bullet will be.
- Error Calculation: The script compares the AI's guess against the "correct" answer from the dataset using a Metric called Mean Squared Error (MSE). This tells the program exactly how far off its prediction was.
- Backward Pass (Backpropagation): This is the "learning" moment. The program works backward from the error to adjust the internal weights of every neuron. It slightly tweaks these weights so that the next time it sees a similar input, its guess will be closer to the correct answer.
4. Momentum and Optimization
To ensure smooth learning, the script uses "inertia momentum." This helps the training process avoid getting stuck in minor mathematical ruts and ensures it moves steadily toward the most accurate solution.
5. Testing and Validation
The script splits its data into two groups: Training and Testing.
- It learns from the Training group.
- It then evaluates its performance on the Testing group—data it has never "seen" before. This confirms that the AI actually learned the underlying physics of the problem rather than just memorizing the answers to the training questions.
The program runs this cycle repeatedly for a set number of iterations until the error is minimized or the maximum number of attempts is reached, ultimately resulting in a model capable of predicting projectile paths based on input variables.
//+------------------------------------------------------------------+
//| MLP_cannonball.mq4 |
//| Copyright © 2008, MetaQuotes Software Corp. |
//| http://www.metaquotes.net |
//+------------------------------------------------------------------+
#property copyright "Copyright © 2008, MetaQuotes Software Corp."
#property link "http://www.metaquotes.net"
/* This program implements a simple Multi Layer Perceptron to solve the canonball problem (regression)
Adapted by Sebastien Marcel (2003-2004) from D. Collobert
The goal is to estimate the position X of a bullet at time t (fixed) given the initial speed (v) and angle (a)
y
/ \
|
|
|
| . X
| .
| .
| .
| .
| .
| .
| .
| .
| .
|. (v,a)
--------------------------> x
*/
#define PI 3.14159265358979323846
#define RAND_MAX 32767.0
//
// Datasets
#define N_PATTERNS_TRAIN 500
#define N_PATTERNS_TEST 500
#define N_PATTERNS_TRAIN_TEST 1000 //N_PATTERNS_TRAIN + N_PATTERNS_TEST
// w1[N_HU1][IN1]=>w1[4][3]
// H In
// | |
// w1[0][0] w1[0][1] w1[0][2]
// w1[1][0] w1[1][1] w1[1][2]
// w1[2][0] w1[2][1] w1[2][2]
// w1[3][0] w1[3][1] w1[3][2]
// forward train:
// aHidden[0] = xBias;
// aHidden[1] = xBias*w1[1][0] + (In0)*w1[1][1] + (In1)*w1[1][2];
// aHidden[2] = xBias*w1[2][0] + (In0)*w1[2][1] + (In1)*w1[2][2];
// aHidden[3] = xBias*w1[3][0] + (In0)*w1[3][1] + (In1)*w1[3][2];
// yHidden[0] = xBias;
// yHidden[1] = f(aHidden[1]);
// yHidden[2] = f(aHidden[2]);
// yHidden[3] = f(aHidden[3]);
//
// w2[OUT][N_HU1]=>w2[2][4]
//
// w2[0][0] w2[0][1] w2[0][2] w2[0][3]
// w2[1][0] w2[1][1] w2[1][2] w2[1][3]
// | |
// Out H
// forward train:
// aOutput[0] = 0.0;
// aOutput[1] = 0.0;
// aOutput[0] = aOutput[0] + yHidden[0]*w2[0][0];
// aOutput[1] = aOutput[1] + yHidden[0]*w2[1][0];
// aOutput[0] = aOutput[0] + yHidden[1]*w2[0][1];
// aOutput[1] = aOutput[1] + yHidden[1]*w2[1][1];
// aOutput[0] = aOutput[0] + yHidden[2]*w2[0][2];
// aOutput[1] = aOutput[1] + yHidden[2]*w2[1][2];
// aOutput[0] = aOutput[0] + yHidden[3]*w2[0][3];
// aOutput[1] = aOutput[1] + yHidden[3]*w2[1][3];
//
// out0 = f(aOutput[0]);
// out1 = f(aOutput[1]);
#define IN 18 //2*9
#define IN1 19 //IN+1
#define OUT 2
#define N_HU 27 //3*9
#define N_HU1 28 //N_HU + 1
//*****************************
// Inputs
//
double DataIn0[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn1[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn2[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn3[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn4[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn5[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn6[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn7[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn8[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn9[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn10[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn11[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn12[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn13[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn14[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn15[N_PATTERNS_TRAIN_TEST]; // angle of bullet
double DataIn16[N_PATTERNS_TRAIN_TEST]; // speed of bullet
double DataIn17[N_PATTERNS_TRAIN_TEST]; // angle of bullet
// X[N_PATTERNS_TRAIN + N_PATTERNS_TEST];
//*****************************
// Targets
//
double DataOut0[N_PATTERNS_TRAIN_TEST]; // x position at time t
double DataOut1[N_PATTERNS_TRAIN_TEST]; // y position at time t
// Y[N_PATTERNS_TRAIN + N_PATTERNS_TEST];
//*****************************
// to create the data
//
double vmax;
double gravity;
//*****************************
// to train the MLP
//
double lambda = 0.01; // learning rate
double mu = 0.6; // inertia momentum rate
double mse_min = 0.001; // minimum Mean Squared Error
int max_iterations = 500; // maximum number of iterations
//*****************************
// MLP data
// weights between hidden neurons and inputs
double w1[N_HU1][IN1];
double w1old[N_HU1][IN1];
// weights between outputs and hidden neurons
double w2[OUT][N_HU1];
double w2old[OUT][N_HU1];
// values of integration function
double aHidden[N_HU1];
double aOutput[OUT];
// values of transfert function
double yHidden[N_HU1];
// constant value of bias
double xBias = 1.0;
int init()
{
vmax = 1.0/10;
gravity = 1.0/200;
return(0);
}
//+------------------------------------------------------------------+
//| script program start function |
//+------------------------------------------------------------------+
int start()
{
//----
initrand();
main();
//----
return(0);
}
//+------------------------------------------------------------------+
//*****************************
// Sigmoid transfer function
//
double f(double x)
{
return (1.0 /(1.0 + MathExp(-x)));
}
//*****************************
// Derivative of Sigmoid
//
double f_prime(double x)
{
double z = MathExp(-x);
double one_plus_z = 1.0 + z;
return (z / (one_plus_z * one_plus_z));
}
//*****************************
// Compute the x position of bullet at time t
//
double xpos(double t, double v, double teta)
{
return( v * t * MathCos(teta*PI/180.0));
}
//*****************************
// Compute the y position of bullet at time t
//
double ypos(double t, double v, double teta)
{
return( -0.5 * gravity * t * t + v * t * MathSin(teta*PI/180.0));
}
//*****************************
// Compute the MSE
//
double MSE(
double a0,
double a1,
double b0,
double b1
)
{
return (0.5*((a0 - b0)*(a0 - b0) + (a1 - b1)*(a1 - b1)));
}
//*****************************
// Create the MLP
//
void createMLP()
{
int i, j;
// weights between hidden neurons and inputs
for (i = 0; i<IN1; i++)
{
for (j = 0; j< N_HU1; j++)
{
w1[j][i] = Random(-1.0, 1.0);
w1old[j][i] = w1[j][i];
}
}
// weights between outputs and hidden neurons
for (i = 0; i<OUT; i++)
{
for (j = 0; j< N_HU1; j++)
{
w2[i][j] = Random(-1.0, 1.0);
w2old[i][j] = w2[i][j];
}
}
}
//*****************************
// Create the datasets
//
void createDatasets()
{
int i;
i = 0;
while (i < (N_PATTERNS_TRAIN + N_PATTERNS_TEST))
{
DataIn0[i] = (Random(0.0, vmax)) / vmax;
DataIn1[i] = (Random(0.0, 90.0)) / 90.0;
DataIn2[i] = (Random(0.0, vmax)) / vmax;
DataIn3[i] = (Random(0.0, 90.0)) / 90.0;
DataIn4[i] = (Random(0.0, vmax)) / vmax;
DataIn5[i] = (Random(0.0, 90.0)) / 90.0;
DataIn6[i] = (Random(0.0, vmax)) / vmax;
DataIn7[i] = (Random(0.0, 90.0)) / 90.0;
DataIn8[i] = (Random(0.0, vmax)) / vmax;
DataIn9[i] = (Random(0.0, 90.0)) / 90.0;
DataIn10[i] = (Random(0.0, vmax)) / vmax;
DataIn11[i] = (Random(0.0, 90.0)) / 90.0;
DataIn12[i] = (Random(0.0, vmax)) / vmax;
DataIn13[i] = (Random(0.0, 90.0)) / 90.0;
DataIn14[i] = (Random(0.0, vmax)) / vmax;
DataIn15[i] = (Random(0.0, 90.0)) / 90.0;
DataIn16[i] = (Random(0.0, vmax)) / vmax;
DataIn17[i] = (Random(0.0, 90.0)) / 90.0;
DataOut0[i] = xpos(10, DataIn0[i] * vmax, (DataIn1[i])*90.0);
DataOut1[i] = ypos(10, DataIn0[i] * vmax, (DataIn1[i])*90.0);
if (DataOut1[i] > 0.0) i = i + 1;
}
}
//*****************************
// Forward the input in the MLP
//
void forward(
double In0,
double In1,
double In2,
double In3,
double In4,
double In5,
double In6,
double In7,
double In8,
double In9,
double In10,
double In11,
double In12,
double In13,
double In14,
double In15,
double In16,
double In17,
double &out0,
double &out1
)
{
int i;
aHidden[0] = xBias;
yHidden[0] = xBias;
for (i = 1; i <= N_HU; i++)
{
aHidden[i] = xBias*w1[i][0] +
(In0)*w1[i][1] +
(In1)*w1[i][2] +
(In2)*w1[i][3] +
(In3)*w1[i][4] +
(In4)*w1[i][5] +
(In5)*w1[i][6] +
(In6)*w1[i][7] +
(In7)*w1[i][8] +
(In8)*w1[i][9] +
(In9)*w1[i][10] +
(In10)*w1[i][11] +
(In11)*w1[i][12] +
(In12)*w1[i][13] +
(In13)*w1[i][14] +
(In14)*w1[i][15] +
(In15)*w1[i][16] +
(In16)*w1[i][17] +
(In17)*w1[i][18] ;
yHidden[i] = f(aHidden[i]);
}
aOutput[0] = 0.0;
aOutput[1] = 0.0;
for (i = 0; i <= N_HU; i++)
{
aOutput[0] = aOutput[0] + yHidden[i]*w2[0][i];
aOutput[1] = aOutput[1] + yHidden[i]*w2[1][i];
}
out0 = f(aOutput[0]);
out1 = f(aOutput[1]);
}
//*****************************
// Backward (back-propagate the gradient of error)
//
void backward(
double Yestimate0,
double Yestimate1,
double Outwant0,
double Outwant1,
double In0,
double In1,
double In2,
double In3,
double In4,
double In5,
double In6,
double In7,
double In8,
double In9,
double In10,
double In11,
double In12,
double In13,
double In14,
double In15,
double In16,
double In17,
double lambda,
double mu
)
{
double wnew, Goutput[OUT], Ghidden[N_HU1];
int i,j;
//
Goutput[0] = (Yestimate0 - Outwant0) * f_prime(aOutput[0]);
Goutput[1] = (Yestimate1 - Outwant1) * f_prime(aOutput[1]);
//
for (i = 0; i<=N_HU; i++)
Ghidden[i] = (Goutput[0]*w2[0][i] + Goutput[1]*w2[1][i])*f_prime(aHidden[i]);
//
for (j = 0; j<OUT;j++)
{
for (i = 0; i<=N_HU; i++)
{
wnew = w2[j][i] - lambda * yHidden[i] * Goutput[j] + mu * (w2[j][i] - w2old[j][i]);
w2old[j][i] = w2[j][i];
w2[j][i] = wnew;
}
}
//
for (i = 0; i<=N_HU; i++)
{
wnew = w1[i][0] - lambda * xBias * Ghidden[i] + mu * (w1[i][0] - w1old[i][0]);
w1old[i][0] = w1[i][0];
w1[i][0] = wnew;
wnew = w1[i][1] - lambda * In0 * Ghidden[i] + mu * (w1[i][1] - w1old[i][1]);
w1old[i][1] = w1[i][1];
w1[i][1] = wnew;
wnew = w1[i][2] - lambda * In1 * Ghidden[i] + mu * (w1[i][2] - w1old[i][2]);
w1old[i][2] = w1[i][2];
w1[i][2] = wnew;
wnew = w1[i][3] - lambda * In2 * Ghidden[i] + mu * (w1[i][3] - w1old[i][3]);
w1old[i][3] = w1[i][3];
w1[i][3] = wnew;
wnew = w1[i][4] - lambda * In3 * Ghidden[i] + mu * (w1[i][4] - w1old[i][4]);
w1old[i][4] = w1[i][4];
w1[i][4] = wnew;
wnew = w1[i][5] - lambda * In4 * Ghidden[i] + mu * (w1[i][5] - w1old[i][5]);
w1old[i][5] = w1[i][5];
w1[i][5] = wnew;
wnew = w1[i][6] - lambda * In5 * Ghidden[i] + mu * (w1[i][6] - w1old[i][6]);
w1old[i][6] = w1[i][6];
w1[i][6] = wnew;
wnew = w1[i][7] - lambda * In6 * Ghidden[i] + mu * (w1[i][7] - w1old[i][7]);
w1old[i][7] = w1[i][7];
w1[i][7] = wnew;
wnew = w1[i][8] - lambda * In7 * Ghidden[i] + mu * (w1[i][8] - w1old[i][8]);
w1old[i][8] = w1[i][8];
w1[i][8] = wnew;
wnew = w1[i][9] - lambda * In8 * Ghidden[i] + mu * (w1[i][9] - w1old[i][9]);
w1old[i][9] = w1[i][9];
w1[i][9] = wnew;
wnew = w1[i][10] - lambda * In9 * Ghidden[i] + mu * (w1[i][10] - w1old[i][10]);
w1old[i][10] = w1[i][10];
w1[i][10] = wnew;
wnew = w1[i][11] - lambda * In10 * Ghidden[i] + mu * (w1[i][11] - w1old[i][11]);
w1old[i][11] = w1[i][11];
w1[i][11] = wnew;
wnew = w1[i][12] - lambda * In11 * Ghidden[i] + mu * (w1[i][12] - w1old[i][12]);
w1old[i][12] = w1[i][12];
w1[i][12] = wnew;
wnew = w1[i][13] - lambda * In12 * Ghidden[i] + mu * (w1[i][13] - w1old[i][13]);
w1old[i][13] = w1[i][13];
w1[i][13] = wnew;
wnew = w1[i][14] - lambda * In13 * Ghidden[i] + mu * (w1[i][14] - w1old[i][14]);
w1old[i][14] = w1[i][14];
w1[i][14] = wnew;
wnew = w1[i][15] - lambda * In14 * Ghidden[i] + mu * (w1[i][15] - w1old[i][15]);
w1old[i][15] = w1[i][15];
w1[i][15] = wnew;
wnew = w1[i][16] - lambda * In15 * Ghidden[i] + mu * (w1[i][16] - w1old[i][16]);
w1old[i][16] = w1[i][16];
w1[i][16] = wnew;
wnew = w1[i][17] - lambda * In16 * Ghidden[i] + mu * (w1[i][17] - w1old[i][17]);
w1old[i][17] = w1[i][17];
w1[i][17] = wnew;
wnew = w1[i][18] - lambda * In17 * Ghidden[i] + mu * (w1[i][18] - w1old[i][18]);
w1old[i][18] = w1[i][18];
w1[i][18] = wnew;
}
}
//*****************************
// Stochastic gradient training
//
double train(int P)
{
double Yestimate0;
double Yestimate1;
double mse_;
double mse_total;
mse_total = 0.0;
// For each train patterns
for(int p = 0 ; p < P ; p++)
{
// Forward current train pattern into the MLP
forward(
//X[p],
DataIn0[p],
DataIn1[p],
DataIn2[p],
DataIn3[p],
DataIn4[p],
DataIn5[p],
DataIn6[p],
DataIn7[p],
DataIn8[p],
DataIn9[p],
DataIn10[p],
DataIn11[p],
DataIn12[p],
DataIn13[p],
DataIn14[p],
DataIn15[p],
DataIn16[p],
DataIn17[p],
//&Yestimate
Yestimate0,
Yestimate1
);
// Computes the MSE
mse_ = MSE(
//Y[p],
DataOut0[p],
DataOut1[p],
//Yestimate
Yestimate0,
Yestimate1
);
// Accumulate the MSE
mse_total = mse_total + mse_;
// Backward MSE gradient
backward(
//Yestimate,
Yestimate0,
Yestimate1,
//Y[p],
DataOut0[p], //Outwant
DataOut1[p], //Outwant
//X[p],
DataIn0[p],
DataIn1[p],
DataIn2[p],
DataIn3[p],
DataIn4[p],
DataIn5[p],
DataIn6[p],
DataIn7[p],
DataIn8[p],
DataIn9[p],
DataIn10[p],
DataIn11[p],
DataIn12[p],
DataIn13[p],
DataIn14[p],
DataIn15[p],
DataIn16[p],
DataIn17[p],
lambda,
mu
);
}
// Return normalized train MSE
double P1=P;
return (mse_total /P1);
}
//
int main()
{
double mse_train;
double mse_test;
double mse_;
double Yestimate0;
double Yestimate1;
//*****************************
createMLP();
//*****************************
createDatasets();
//*****************************
//for (int i = 0; i< N_PATTERNS_TRAIN; i++) printf(" TRN: x=[%f %f] y=[%f %f]\n", X[i].v, X[i].a, Y[i].x, Y[i].y);
//for (int i = N_PATTERNS_TRAIN; i<(N_PATTERNS_TRAIN + N_PATTERNS_TEST); i++) printf(" TST: x=[%f %f] y=[%f %f]\n", X[i].v, X[i].a, Y[i].x, Y[i].y);
Print("Stochastic gradient training:");
//
int pf_train = FileOpen("mse_train_mt4_in18.txt",FILE_CSV|FILE_WRITE,' ');//FileOpen("mse_train.txt", "w");
int pf_test = FileOpen("mse_test_mt4_in18.txt",FILE_CSV|FILE_WRITE,' ');//FileOpen("mse_test.txt", "w");
int iter;
for(iter = 1 ; iter <= max_iterations ; iter++)
{
//*****************************
// train
//*****************************
mse_train = train(N_PATTERNS_TRAIN);
FileWrite(pf_train,mse_train);
//*****************************
// test
//*****************************
mse_test = 0.0;
// For each test pattern
// (N_PATTERNS_TRAIN + N_PATTERNS_TEST) N_PATTERNS_TRAIN 0
// +-----------------------------------------------------------+------------------------------------------+
//
for(int i = N_PATTERNS_TRAIN ; i < (N_PATTERNS_TRAIN + N_PATTERNS_TEST) ; i++)
{
Yestimate0 = 0.0;
Yestimate1 = 0.0;
// forward current pattern into the MLP
//forward(X[i], &Yestimate);
forward(
//X[p],
DataIn0[i],
DataIn1[i],
DataIn2[i],
DataIn3[i],
DataIn4[i],
DataIn5[i],
DataIn6[i],
DataIn7[i],
DataIn8[i],
DataIn9[i],
DataIn10[i],
DataIn11[i],
DataIn12[i],
DataIn13[i],
DataIn14[i],
DataIn15[i],
DataIn16[i],
DataIn17[i],
//&Yestimate
Yestimate0,
Yestimate1
);
// computes MSE
//mse_ = MSE(Y[i], Yestimate);
mse_ = MSE(
//Y[p],
DataOut0[i],
DataOut1[i],
//Yestimate
Yestimate0,
Yestimate1
);
// accumulate MSE
mse_test += mse_;
}
// Normalize the MSE
mse_test /= N_PATTERNS_TEST;
FileWrite(pf_test,mse_test);
Print("->",iter);
//fflush(stdout);
if (mse_train < mse_min) break;
}
//Print("\n");
//
FileClose(pf_test);
FileClose(pf_train);
//*****************************
// Print info about training
//
Print("Number of iterations = ", iter);
Print("Final MSE train = ", mse_train);
Print("Final MSE test = ", mse_test);
Print("End of program.");
return (0);
}
//use this first function to seed the random number generator,
//call this before any of the other functions
void initrand()
{
//srand((unsigned)(time(0)));
MathSrand(TimeLocal());
}
//generates a psuedo-random double between 0.0 and 0.999...
double randdouble0()
{
return (MathRand()/((RAND_MAX)+1));
}
//generates a psuedo-random double between min and max
double randdouble2(double min, double max)
{
if (min>max)
{
return (randdouble0()*(min-max)+max);
}
else
{
return (randdouble0()*(max-min)+min);
}
}
// Random generator
double Random(double inf, double sup)
{
return(randdouble2(inf,sup));
}
Comments