The Code Compass

Home
Notes
Case Studies
Machine Learning Fundamentals
Transformers Series
Archive
About
Transformers and the Power of Positional Encoding [Transformers Series]
How Transformers Find Order In Data
 • 
CodeCompass
"Attention, Please!": A Visual Guide To The Attention Mechanism [Transformers Series]
Develop an intuition behind Attention: why it took over machine learning + LLMs and what it actually does
 • 
CodeCompass
Uber's Billion Dollar Problem: Predicting ETAs Reliably And Quickly
A visual deep dive into how Uber uses graph theory, embeddings and self-attention and to predict ETAs
 • 
CodeCompass
1
Most Popular
View all
How Netflix Uses Machine Learning To Decide What Content To Create Next For Its 260M Users
 • CodeCompass
"Attention, Please!": A Visual Guide To The Attention Mechanism [Transformers Series]
 • CodeCompass
How Tesla Continuously and Automatically Improves Autopilot and Full Self-Driving Capability On 5M+ Cars
 • CodeCompass
How Apple's iPhone Uses Private, On-Device Machine Learning To Recognize People In Photos
 • CodeCompass
2
Uber's Billion Dollar Problem: Predicting ETAs Reliably And Quickly
 • CodeCompass
1
Dropout: A Simple Solution to a Complex Problem
 • CodeCompass
2
How Tesla Continuously and Automatically Improves Autopilot and Full Self-Driving Capability On 5M+ Cars
Learn how to build a data engine that continuously improve your ML models
 • 
CodeCompass
Dropout: A Simple Solution to a Complex Problem
Learn about dropout, its variants and how to apply them in your next project
 • 
CodeCompass
2
How Apple's iPhone Uses Private, On-Device Machine Learning To Recognize People In Photos
Learn how contrastive learning, embeddings and clustering recognize people across a diverse demographic
 • 
CodeCompass
2
How Netflix Uses Machine Learning To Decide What Content To Create Next For Its 260M Users
Learn how metadata, pre-training and embeddings drive decision-making at Netflix
 • 
CodeCompass
Supercharge Your Machine Learning Model Architecture with 1x1 Convolutions
Learn what 1x1 convs are and how to build lightweight and performant CNNs
 • 
CodeCompass
The Code Compass
The Code Compass
Subscribe for weekly visual deep dives into the world of machine learning via real-world case studies, ML fundamentals, and actionable insights in your inbox.
Recommendations
View all 13
The Chip Letter
The Chip Letter
Babbage
Engineering Leadership
Engineering Leadership
Gregor Ojstersek
The Pragmatic Engineer
The Pragmatic Engineer
Gergely Orosz
Latent Space
Latent Space
swyx & Alessio
Product Growth
Product Growth
Aakash Gupta
More From The Code Compass
My Notes
Short thoughts about machine learning, engineering and building a product.

The Code Compass

AboutArchiveRecommendationsSitemap
© 2024 CodeCompass
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture