🧠 Simple Neural Network in C ⚙️

A lightweight, from-scratch implementation of a feedforward neural network in pure C. This project demonstrates the fundamental principles of neural networks by teaching a simple model to solve the classic XOR problem.

---

✨ Features

• Pure C: Built with only standard C libraries (stdlib.h, stdio.h, math.h). No heavy dependencies!
• Feedforward Architecture: A simple and classic neural network structure with an input layer, a hidden layer, and an output layer.
• Backpropagation Algorithm: Learns from its mistakes by propagating errors backward through the network to adjust weights and biases.
• Sigmoid Activation: Uses the sigmoid function to introduce non-linearity, allowing it to learn complex patterns.
• Stochastic Training: Shuffles the training data for each epoch to prevent the model from getting stuck in local minima and improve generalization.

---

🚀 How to Get Started

You can compile and run this project with any standard C compiler like GCC.

Prerequisites

• A C compiler (e.g., GCC)

Compilation

1. Clone the repository:

   git clone [https://github.com/Anjas2005/Neural-Network-in-C.git](https://github.com/Anjas2005/Neural-Network-in-C.git)
   cd Neural-Network-in-C

2. Compile the C code. The -lm flag is necessary to link the math library.

   gcc main.c -o neural_network -lm

Execution

Run the compiled executable from your terminal:

./neural_network

---