Neural Logic Gates

This repository contains implementations of basic logic gates (AND, OR, NOT, XOR) using artificial neural networks (ANNs) with TensorFlow/Keras. Each script trains a neural network to approximate the behavior of its respective logic gate.

📌 Overview

Each Python script defines, trains, and evaluates a neural network to mimic a specific logic gate:

• and.py – Simulates an AND gate.
• or.py – Simulates an OR gate.
• not.py – Simulates a NOT gate.
• xor.py – Simulates an XOR gate.

The models use a simple feedforward neural network architecture with fully connected layers.

🚀 Requirements

Ensure you have the following dependencies installed before running the scripts:

pip install numpy tensorflow keras

🏗️ Model Architecture

• Each model consists of one or more dense (fully connected) layers.
• Activation functions used: ReLU, Tanh, and Sigmoid.
• Optimizer: Adam.
• Loss function: binary_crossentropy (for classification tasks).

🔧 Usage

Run the desired logic gate script to train and evaluate the neural network:

python and.py
python or.py
python not.py
python xor.py

After training, the model evaluates its accuracy and prints predictions based on the input dataset.

📊 Example Output (AND Gate)

binary_accuracy: 100.00%
[[0.]
 [0.]
 [0.]
 [1.]]