Simple Neutral Network from scratch

neural_network.py

# This program was generated by ChatGPT

import numpy as np

# Sigmoid activation function
def sigmoid(x):
    return 1 / (1 + np.exp(-x))

# Derivative of the sigmoid function
def sigmoid_derivative(x):
    return x * (1 - x)

# Define the neural network class
class NeuralNetwork:
    def __init__(self, input_size, hidden_size, output_size):
        # Initialize weights and biases with random values
        self.weights_input_hidden = np.random.rand(input_size, hidden_size)
        self.bias_hidden = np.zeros((1, hidden_size))
        self.weights_hidden_output = np.random.rand(hidden_size, output_size)
        self.bias_output = np.zeros((1, output_size))

    def forward(self, X):
        # Forward pass through the network
        self.hidden_input = np.dot(X, self.weights_input_hidden) + self.bias_hidden
        self.hidden_output = sigmoid(self.hidden_input)
        self.final_input = np.dot(self.hidden_output, self.weights_hidden_output) + self.bias_output
        self.predictions = sigmoid(self.final_input)
        return self.predictions

    def backward(self, X, y, learning_rate):
        # Backward pass to update weights and biases
        error = y - self.predictions
        output_delta = error * sigmoid_derivative(self.predictions)

        hidden_error = output_delta.dot(self.weights_hidden_output.T)
        hidden_delta = hidden_error * sigmoid_derivative(self.hidden_output)

        # Update weights and biases
        self.weights_hidden_output += self.hidden_output.T.dot(output_delta) * learning_rate
        self.bias_output += np.sum(output_delta, axis=0, keepdims=True) * learning_rate
        self.weights_input_hidden += X.T.dot(hidden_delta) * learning_rate
        self.bias_hidden += np.sum(hidden_delta, axis=0, keepdims=True) * learning_rate

    def train(self, X, y, epochs, learning_rate):
        # Training loop
        for epoch in range(epochs):
            # Forward pass
            predictions = self.forward(X)

            # Backward pass
            self.backward(X, y, learning_rate)

            # Calculate and print the mean squared error
            mse = np.mean(np.square(y - predictions))
            if epoch % 100 == 0:
                print(f"Epoch {epoch}, Mean Squared Error: {mse}")

# Create a simple dataset for XOR-like behavior
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])

# Create and train the neural network
input_size = 2
hidden_size = 4
output_size = 1
learning_rate = 0.1
epochs = 10000

# Instantiate the neural network
nn = NeuralNetwork(input_size, hidden_size, output_size)

# Train the neural network
nn.train(X, y, epochs, learning_rate)

# Make predictions
predictions = nn.forward(X)
print("\nFinal Predictions:")
print(predictions)