Formal Algorithms for Transformers arxiv.org ↗
A paper giving precise pseudocode descriptions of transformer architectures.
OtherLearning & bookstransformersattentionpaper
Captured
Recommended in 1 thread
The Little Book of Generative AI Foundations: An Intuitive Mathematical Primerarxiv.org ·
Called the most succinct introduction to attention.
Similar tools
- How Transformer LLMs Work ↗Learning & books1 thread
A DeepLearning.AI course explaining transformer language model internals.
- Probabilistic Artificial Intelligence ↗Learning & books1 thread
A freely available textbook on probabilistic approaches to AI, published on arXiv.
- Professional Linux Kernel Architecture ↗Learning & books1 thread
A book by Wolfgang Mauerer describing Linux kernel internals.
- Handbook of Applied Cryptography ↗Learning & books1 thread
A reference book on classic cryptographic algorithms and protocols.
- Thinking Like Transformers ↗AI & ML0 threads
ICML 2021 paper introducing RASP, a language for expressing computations transformers can perform.
- Why Machines Learn ↗Learning & books1 thread
A book by Anil Ananthaswamy explaining the math behind modern AI.
- 1 thread
- 0 threads
Also in Learning & books
- Careless People ↗3 threads
A memoir by former Facebook executive Sarah Wynn-Williams about the company's leadership.
- 3 threads
- 3 threads
- Wikipedia3 threads
A free collaborative online encyclopedia.
- 2 threads
- 2 threads
- Diátaxis ↗2 threads
A framework for organising technical documentation into tutorials, how-tos, reference and explanation.
- 2 threads
- 2 threads
- How Complex Systems Fail ↗2 threads
A short essay by Richard Cook on the nature of failure in complex systems.
- 2 threads
- 2 threads
Link from a commenter, not checked or endorsed by us: ↗ https://arxiv.org/pdf/2207.09238