C++ Handwritten Digit Neural Network Classifier from Scratch with GUI

• Skills & Tools: C++, SFML
• Github URL: Project Link
• GUI Demonstration: YouTube Link

Engineered a complete neural network framework in native C++ supporting ReLU, Linear and Softmax layers.

Intentionally designed to be modular and object-oriented for scalability, adding new layers and tools

Implemented model serialization and an SFML interactive Graphical User Interface for digit drawing and prediction.

There is a training config to specify training hyperparameters. The framework supports fully functional forward and backward propagation with gradient descent.

Model's can be loaded and saved seamlessly by writing model weights to a .txt file.