Skip to content

README.md

Latest commit

 

History

History
95 lines (62 loc) · 2.6 KB

README.md

File metadata and controls

95 lines (62 loc) · 2.6 KB

🧠 Neural Network From Scratch – MNIST Digit Recognizer

License

This project implements a Neural Network from scratch in Python using only NumPy to recognize handwritten digits from the MNIST dataset. It’s an educational project designed to understand how neural networks work internally without relying on high-level libraries like TensorFlow or PyTorch.

🚀 Features

✅ Builds a neural network from scratch (no external ML frameworks)
✅ Implements forward propagation and backpropagation
✅ Uses ReLU and Softmax activations
✅ Trains on the MNIST dataset
✅ Achieves ~85% accuracy on the development set
✅ Visualizes predictions for test images

🛠️ Tech Stack

  • Language: Python 🐍
  • Libraries: NumPy, Pandas, Matplotlib
  • Dataset: MNIST (handwritten digits)

📥 Installation

1️⃣ Clone the repository

git clone https://github.com/chetlasrijith/neural-net-mnist.git
cd neural-net-mnist

2️⃣ Install dependencies

pip install numpy pandas matplotlib

3️⃣ Add Dataset

  • Download the MNIST training dataset (mnist_train.csv) from Kaggle or any other source.
  • Place the file in the datasets/ folder.

🧑‍💻 How It Works

  1. Data Loading: Loads mnist_train.csv, normalizes pixel values (0-1).

  2. Network Architecture:

    • Input layer: 784 neurons (28x28 pixels)
    • Hidden layer: 10 neurons with ReLU activation
    • Output layer: 10 neurons with Softmax activation

  3. Training:

    • Uses forward propagation to compute predictions.
    • Applies backpropagation to update weights and biases.
    • Trains over multiple iterations (epochs).

  4. Prediction:

    • Predicts the digit for unseen images and visualizes them using Matplotlib.

📊 Results

Metric Value
Training Accuracy 85%
Test Accuracy ~84-85%

🤝 Contributing

Contributions are welcome! Follow these steps:

  1. Fork the repo
  2. Create your branch (git checkout -b feature/new-feature)
  3. Commit your changes (git commit -m 'Add new feature')
  4. Push to the branch (git push origin feature/new-feature)
  5. Open a Pull Request

📞 Contact

Created with ❤️ by Chetla Srijith For queries, raise an issue in the repository or connect on LinkedIn.