Alice’s Adventures in a Differentiable Wonderland
A friendly primer on differentiable programming and neural nets—covering autodiff, CNNs, RNNs, transformers in PyTorch & JAX.
arXiv.orgAlice's Adventures in a Differentiable Wonderland -- Volume I, A Tour of the LandNeural 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.
Markdown Editor Enhancer для Mastodon (GlitchSoc only)
)
Для чего использовать?
Перед отправкой — чтобы не было сюрпризов: убедиться, что текст отформатирован правильно и не развалится на выходе.
После отправки — можно перечитать готовый пост, выловить ошибки или исправить, добавить что-то не вылезая из ленты: (монжо легко очистить окно, нажав Escape).
Ахтунг! Поддерживается только на серверах с 