Build a Deep Learning Library

This tutorial teaches readers how to build their own deep learning library from scratch using only a blank file and NumPy, rather than simply learning to use existing frameworks. The project guides users through creating a complete autograd engine and collection of neural network layer modules that can actually train models. By completion, the custom-built library becomes functional enough to successfully train popular machine learning models including MNIST digit recognition, convolutional neural networks, and ResNet architectures.