Note Management System

Edit Note

Title:

Content:

class NeuralNetwork {     private $layers; // Array defining the number of neurons in each layer
Example in a Real-World Scenario:
Imagine you're creating a neural network to predict whether someone will buy a product based on 3 factors:

Age
Salary
Years of Experience
In this case, the input layer will have 3 neurons (one for each factor), and you will input data such as:

Age = 25
Salary = 50,000
Years of Experience = 5

OR 
 Predicting House Price
Predicting Student Graduation
Email Spam Classifier
Email Spam Classifier
Predicting Customer Churn (Telecom)
Predicting Health Risk (Diabetes Prediction)

///////////////////////////////////////////////////1 example////////////////////////////////////////////

<?php

class SimpleNeuralNetwork {
    private $layers; // Array defining the number of neurons in each layer

public function __construct($layers) {
        // Initialize the layers
        $this->layers = $layers;
    }

public function feedForward($input) {
        $output = $input;

// Simulating feedforward process through layers
        for ($i = 1; $i < count($this->layers); $i++) {
            // For simplicity, just passing the input to the next layer
            // In a real neural network, you'd apply a matrix multiplication with weights and biases here
            $output = $this->activate($output); // Apply an activation function (e.g., sigmoid)
        }
        return $output;
    }

private function activate($x) {
        // Sigmoid activation function for simplicity
        // Check if $x is an array and apply sigmoid element-wise
        if (is_array($x)) {
            foreach ($x as &$value) {
                $value = 1 / (1 + exp(-$value)); // Apply sigmoid element-wise
            }
        } else {
            $x = 1 / (1 + exp(-$x)); // Apply sigmoid to scalar
        }
        return $x;
    }
}

// Example usage: Creating a simple neural network with 3 input neurons and 1 output neuron
$nn = new SimpleNeuralNetwork([3, 2, 1]); // 3 inputs, 2 hidden neurons, 1 output

if ($_SERVER['REQUEST_METHOD'] === 'POST') {
    // Gather input data
    $input = [
        floatval($_POST['age']),
        floatval($_POST['salary']),
        floatval($_POST['experience']),
    ];

// Perform the feedforward operation
    $output = $nn->feedForward($input);

// Extract the scalar value from the output (since it's an array with one element)
    $predictedOutput = is_array($output) ? $output[0] : $output;

// Show prediction and probability
    echo "Prediction: " . ($predictedOutput > 0.5 ? "Will Buy" : "Won't Buy");
    echo "<br>Predicted Probability: " . number_format($predictedOutput, 4);
}
?>

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Neural Network Prediction</title>
</head>
<body>
    <h1>Simple Neural Network Prediction</h1>

<label for="salary">Salary:</label>
        <input type="number" step="any" id="salary" name="salary" required><br>

<label for="experience">Years of Experience:</label>
        <input type="number" step="any" id="experience" name="experience" required><br>

</body>
</html>
//////////////////////////////////////////////////////////

<?php

class NeuralNetwork {
    private $layers; // Array defining the number of neurons in each layer
    private $weights; // Weights for each layer
    private $biases;  // Bias values for each layer

public function __construct($layers) {
        $this->layers = $layers;
        $this->weights = [];
        $this->biases = [];

// Initialize weights and biases with random values
        for ($i = 1; $i < count($layers); $i++) {
            $this->weights[$i] = $this->randomMatrix($layers[$i], $layers[$i-1]);
            $this->biases[$i] = $this->randomMatrix($layers[$i], 1);
        }
    }

private function randomMatrix($rows, $cols) {
        // Generate a matrix with random values between -1 and 1
        $matrix = [];
        for ($i = 0; $i < $rows; $i++) {
            for ($j = 0; $j < $cols; $j++) {
                $matrix[$i][$j] = mt_rand(-1000, 1000) / 1000; // Random value between -1 and 1
            }
        }
        return $matrix;
    }

public function feedForward($input) {
        $output = $input;

// Feed the input through the layers
        for ($i = 1; $i < count($this->layers); $i++) {
            // Matrix multiplication of inputs and weights + bias
            $output = $this->sigmoid($this->matrixAdd($this->matrixMultiply($this->weights[$i], $output), $this->biases[$i]));
        }
        return $output;
    }

private function sigmoid($x) {
        if (is_array($x)) {
            // Apply sigmoid to each element in the array (element-wise)
            foreach ($x as &$row) {
                foreach ($row as &$value) {
                    $value = 1 / (1 + exp(-$value));
                }
            }
        } else {
            $x = 1 / (1 + exp(-$x));
        }
        return $x;
    }

private function matrixMultiply($a, $b) {
        $rowsA = count($a);
        $colsA = count($a[0]);
        $colsB = count($b[0]);
        $result = [];

for ($i = 0; $i < $rowsA; $i++) {
            for ($j = 0; $j < $colsB; $j++) {
                $sum = 0;
                for ($k = 0; $k < $colsA; $k++) {
                    $sum += $a[$i][$k] * $b[$k][$j];
                }
                $result[$i][$j] = $sum;
            }
        }
        return $result;
    }

private function matrixAdd($a, $b) {
        $rows = count($a);
        $cols = count($a[0]);
        $result = [];

for ($i = 0; $i < $rows; $i++) {
            for ($j = 0; $j < $cols; $j++) {
                $result[$i][$j] = $a[$i][$j] + $b[$i][$j];
            }
        }
        return $result;
    }
}

// Initialize neural network with 5 input features, 4 hidden neurons, and 1 output
$nn = new NeuralNetwork([5, 4, 1]);

// Ensure that the form is submitted and the POST data exists
if ($_SERVER['REQUEST_METHOD'] === 'POST') {
    if (isset($_POST['age'], $_POST['salary'], $_POST['experience'], $_POST['education'], $_POST['marital_status'], $_POST['location'])) {
        // Get input values and convert them to float for processing
        $input = [
            [floatval($_POST['age'])],
            [floatval($_POST['salary'])],
            [floatval($_POST['experience'])],
            [floatval($_POST['education'])], // This is an example; adjust based on your input type
            [floatval($_POST['marital_status'])], // Likewise, adjust based on your input type
            [floatval($_POST['location'])] // Adjust based on your input type
        ];

// Perform the feedforward operation to get the predicted output
        $output = $nn->feedForward($input);
        $prediction = $output[0][0] >= 0.5 ? "Will Buy" : "Won't Buy";

// Display the result
        echo "Prediction: $prediction<br>";
        echo "Predicted Probability: " . number_format($output[0][0], 4);
    } else {
        echo "Please fill in all the fields.";
    }
} else {
    // Show initial form if the page is accessed without submission
    echo "Please submit the form to get a prediction.";
}
?>

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Predict Product Purchase</title>
</head>
<body>
    <h1>Predict if someone will buy a product</h1>

<label for="salary">Salary:</label>
        <input type="number" step="any" id="salary" name="salary" required><br>

<label for="experience">Years of Experience:</label>
        <input type="number" step="any" id="experience" name="experience" required><br>

<label for="education">Education Level:</label>
        <select id="education" name="education" required>
            <option value="1">High School</option>
            <option value="2">Bachelor's</option>
            <option value="3">Master's</option>
            <option value="4">PhD</option>
        </select><br>

<label for="marital_status">Marital Status:</label>
        <select id="marital_status" name="marital_status" required>
            <option value="0">Single</option>
            <option value="1">Married</option>
        </select><br>

<label for="location">Location:</label>
        <input type="text" id="location" name="location" required><br>

</body>
</html>