An open-source deep learning educational resource teaching concepts through interactive Jupyter notebooks that integrate exposition, figures, math equations, and self-contained code. The book covers multiple ML frameworks including PyTorch, TensorFlow, JAX, MXNet, and Keras across topics like computer vision, NLP, reinforcement learning, and recommender systems. Originally developed for UC Berkeley’s STAT 157 course, it has been adopted by hundreds of universities across 70 countries.