Add artificial_neural_network.py in neural_network

[AHuzail]

Simple Artificial Neural Network (ANN) Implementation

Description:

This PR adds a basic implementation of a feedforward Artificial Neural Network (ANN) using Python and NumPy. The network consists of one hidden layer and uses Sigmoid activation, backpropagation with gradient descent, and Mean Squared Error (MSE) as the loss function. It demonstrates a solution to the XOR problem, commonly used in introductory neural network tutorials.

Key Features:

• Feedforward neural network with 1 hidden layer.
• Sigmoid activation function.
• Gradient Descent optimizer for weight updates.
• Mean Squared Error (MSE) loss function.
• Example provided to solve the XOR problem.

Checklist:

• [x] Code follows the repository's contribution guidelines.
• [x] Tests have been added or updated.
• [x] Documentation has been updated (if applicable).
• [x] Code is well-documented with comments and descriptions.

• [ X] Add an algorithm?

Checklist:

• [ X] I have read CONTRIBUTING.md.
• [ X] This pull request is all my own work -- I have not plagiarized.
• [ X] I know that pull requests will not be merged if they fail the automated tests.
• [ X] This PR only changes one algorithm file. To ease review, please open separate PRs for separate algorithms.
• [ X] All new Python files are placed inside an existing directory.
• [ X] All filenames are in all lowercase characters with no spaces or dashes.
• [ X] All functions and variable names follow Python naming conventions.
• [ X] All function parameters and return values are annotated with Python type hints.
• [ X] All functions have doctests that pass the automated testing.
• [ X] All new algorithms include at least one URL that points to Wikipedia or another similar explanation.