Все публикации

0:14:38

A better way to think about Taylor series #SoMEpi

0:31:51

MAMBA from Scratch: Neural Nets Better and Faster than Transformers

0:20:18

Why Does Diffusion Work Better than Auto-Regression?

0:18:08

Transformer Neural Networks Derived from Scratch

0:16:30

Why do Convolutional Neural Networks work so well?