THIS is why large language models can understand the world
Algorithmic Simplicity
THIS is why large language models can understand the world
18:08
A better way to think about Taylor series #SoMEpi
Algorithmic Simplicity
A better way to think about Taylor series #SoMEpi
14:38
MAMBA from Scratch: Neural Nets Better and Faster than Transformers
Algorithmic Simplicity
MAMBA from Scratch: Neural Nets Better and Faster than Transformers
31:51
Why Does Diffusion Work Better than Auto-Regression?
Algorithmic Simplicity
Why Does Diffusion Work Better than Auto-Regression?
20:18
Transformer Neural Networks Derived from Scratch
Algorithmic Simplicity
Transformer Neural Networks Derived from Scratch
18:08
Why do Convolutional Neural Networks work so well?
Algorithmic Simplicity
Why do Convolutional Neural Networks work so well?
16:30
But what is a neural network REALLY?
Algorithmic Simplicity
But what is a neural network REALLY?
11:17