A practical, code-first look at DeepMind's new haiku library.
Exploring 6 noteworthy approaches for incorporating longer-term context in transformer models.
Leveraging annotator rationales for more interpretable and sample efficient classification.
Time and memory efficient alternatives to vanilla transformers through locality sensitive hashing and reversible layers.
Put on your metaphorical safety goggles and start building something weird with JAX.
Building intuition for Receiving Operator Characterstic (ROC) curves and what they measure through visualization.
Musings on extensions to einsum notation for more readable machine learning code.
Processing your application
There was an error sending the email, please try again
Check your inbox and click the link to confirm your subscription
machine learning musings
You've successfully subscribed to machine learning musings
Welcome back! You've successfully signed in.
Great! You've successfully signed up.
Success! Your account is fully activated, you now have access to all content.