AI by Hand ✍️

AI by Hand ✍️

Home
Frontier
Foundation
🏫 Academy

Walkthrough

Adding Two Arrays in GPU by Hand ✍️
I drew 42 frames to show how a GPU speeds up an array operation of 8 elements in parallel over 4 threads in 2 clock cycles.
 • Prof. Tom Yeh
Context Engineering by Hand ✍️
There has been a lot of talks about context engineering.
 • Prof. Tom Yeh
Matmul on GPU/TPU by Hand ✍️
I drew 91 frames to show how to divide large matrices into "tiles" to use accelerators such as GPU/TPU.
 • Prof. Tom Yeh
BitNet by Hand ✍️
This week, Mohamed Mekkouri from Hugging Face published a blog post to share their success in fine-tuning LLMs to 1.58bit.
 • Prof. Tom Yeh
Discrete Fourier Transform by Hand ✍️
In signal processing, the Discrete Fourier Transform (DFT) is no doubt the most important method.
 • Prof. Tom Yeh
Superposition by Hand ✍️
Superposition is a key property that differentiates a qubit in a quantum computer from a bit in a classical computer.
 • Prof. Tom Yeh
LSTM by Hand ✍️
 • Prof. Tom Yeh
Sparse Auto Encoder (SAE) by Hand ✍️
Earlier this week, Anthropic published a paper on their latest effort toward interpretable AI:
 • Prof. Tom Yeh
Variational Auto Encoder (VAE) by Hand ✍️
A Variational Auto Encoder (VAE) learns the structure (mean and variance) of hidden features and generates new data from the learned structure.
 • Prof. Tom Yeh
Deep RNN by Hand ✍️
A Deep Recurrent Neural Network (RNN) extends a basic single-layer RNN into multiple layers of hidden states, effectively incorporating deep learning…
 • Prof. Tom Yeh
SVM by Hand ✍️
Support Vector Machines (SVMs) reigned supreme in machine learning before the ascendancy of the deep learning revolution.
 • Prof. Tom Yeh
U-Net by Hand ✍️
Thanks for reading AI by Hand ✍️!
 • Prof. Tom Yeh
© 2026 Tom Yeh · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture