Alice's Adventures in a Differentiable Wonderland -- Volume I, A Tour of the Land
This is an incremental educational resource for newcomers to machine learning and AI, offering a foundational overview without introducing new methods or data.
The paper provides an introductory primer on differentiable programming, focusing on neural network design techniques like convolutional, attentional, and recurrent blocks to bridge theory and code, aiming to equip readers with the understanding needed for advanced models such as large language models and multimodal architectures.
Neural networks surround us, in the form of large language models, speech transcription systems, molecular discovery algorithms, robotics, and much more. Stripped of anything else, neural networks are compositions of differentiable primitives, and studying them means learning how to program and how to interact with these models, a particular example of what is called differentiable programming. This primer is an introduction to this fascinating field imagined for someone, like Alice, who has just ventured into this strange differentiable wonderland. I overview the basics of optimizing a function via automatic differentiation, and a selection of the most common designs for handling sequences, graphs, texts, and audios. The focus is on a intuitive, self-contained introduction to the most important design techniques, including convolutional, attentional, and recurrent blocks, hoping to bridge the gap between theory and code (PyTorch and JAX) and leaving the reader capable of understanding some of the most advanced models out there, such as large language models (LLMs) and multimodal architectures.