Learn to build a Deep Learning library from scratch in Python and NumPy (autograd, CNNs, ResNets) [free]

Read it for free here: https://zekcrates.quarto.pub/deep-learning-library/
I created this project to strip away the "black box" of modern frameworks and implement the core stuff from a blank file using only Python and NumPy.

What You’ll Build

1. Autograd Engine – automatic differentiation from scratch
2. Neural Network Modules – layers, activations, and loss functions
3. Optimizers – SGD, Adam
4. Model Persistence – save and load trained models
5. Training Loop – a clean, reusable trainer
6. Datasets & Dataloaders – batching, shuffling, iteration
7. Parameter Initialization – common initialization strategies
8. Convolutional Neural Networks (CNNs) – build and train conv nets

What You’ll Train (Using the Library)

1. MNIST – fully train a neural network from scratch
2. Simple CNN on MNIST
3. CNN on CIFAR-10
4. Simple ResNet on CIFAR-10

The project is intended as a conceptual and fun reference rather than a production framework.

Feedback on correctness, scope, or missing pieces would be very welcome.

Read it for free here: https://zekcrates.quarto.pub/deep-learning-library/