Transformers
Reachability and asymptotics of Gaussian Transformer dynamics
💬Natural Language Processing Content type: AcademicELI5 is a terrible learning prompt, here's the structural reason it fails and a 4-level replacement that actually sticks
🧠LLMs Content type: Blog Content type: TutorialMachine learning from scratch, what to build before using scikit-learn
🧠Neural Networks Content type: TutorialSpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks
🤖Machine Learning Content type: AcademicLess-relevant results