This repository is dedicated to the simulation of the McCulloch-Pitts neuron model, one of the earliest neural network models, demonstrating basic logical functions through a network of binary threshold neurons.

• Implements the McCulloch-Pitts neuron model in Python.
• Includes a three-input, three-output network configuration to demonstrate complex logical functions.
• Provides a test suite to evaluate the network's logic for all possible input combinations.
• Demonstrates fundamental concepts of neural computation and early artificial neural networks.

1. Clone the repository.
2. No external libraries required, pure Python implementation.

• The McCulloch-Pitts neuron computes binary output based on weighted input sums and a threshold.
• It represents the basis of logical functions like AND, OR, and NOT through binary operations.

• The ThreeInputThreeOutputNetwork class showcases how neurons can be interconnected to simulate more complex logical operations.
• Each neuron's firing rule is based on its inputs, weights, and threshold, demonstrating basic decision-making processes.

• Run the main function to see the neuron model in action.
• The network processes inputs through its neurons and displays the outputs, illustrating the basic principles of neural information processing.

Interested in contributing? You're welcome to submit pull requests or suggestions to improve the simulations or add more features related to neural network fundamentals.

This project is licensed under the MIT License - see the LICENSE file for more details.

• Respect to Warren S. McCulloch and Walter Pitts for their pioneering work in neural network theory.

For more details and to dive into the fascinating world of neural network models, visit the GitHub repository.