This project implements a simple neural network for digit classification using backpropagation. It is designed to be trained from the MNIST dataset. The project is implemented in C++ using the Eigen library for matrix operations. The development of this project was inspired by the book "Neural Networks and Deep Learning" by Michael Nielsen.
- Backpropagation: Implements the backpropagation algorithm for training the neural network.
- Customizable Architecture: Allows customization of the number of layers and neurons in the network.
- Stochastic Gradient Descent (SGD): Optimizes the network using the SGD method.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.