In data science and machine learning, the structures we use to represent grounded knowledge are increasingly important, but the corresponding names for those structures are often confused and conflated. In this post I'll disambiguate a few of the most common terms and provide examples of how and where they can be applied and misapplied.
Why should we care about uncertainty in machine learning models? And is it even possible to calculate it?
A little bit of trigonometry is all you need to get the most from your datetime features
What's do we mean when we talk about privileged and non-privileged bases in neural networks? How is a basis chosen or trained, and what can we say about their features?
Merging cells with ⇧m
Positional embeddings are key to the success of transformer models like BERT and GPT, but the way they work is often left unexplored. In this deep-dive, I want to break down the problem they're intended to solve and establish an intuitive feel for how they achieve it.
This novel approach to approximate nearest neighbour search achieves super-fast query times by using elasticsearch to index and query the outputs of an LSH model. The cheap, scalable architecture for both hashing and querying make it an ideal approach for huge datasets in production environments.
Generators come to the rescue when your dataset is too big for your machine
My CV is written and styled to be viewed on the web, but some clever javascript creates a downloadable PDF version automatically, every time the site is built!
Share your .env files without their secrets, using dotenv-stripout
Using python and zsh to create secure random strings whenever I need them
Making my terminal tabs more readable with git and zsh
Making sure that what I build works for everyone, all the time
How I set a unique emoji as the favicon for each page on this website
You can, and should make anti-racism part of your day-to-day work
How do you do relative imports in python??