For many of you who are machine learning practitioners, I know precision and recall are metrics you know like the back of your hand for evaluating classification models. I thought I’d run across most things related to precision and recall, but I recently encountered something surprising (at least to me!)

Let’s say you are an analyst and you want to know the fraction of companies which discuss carbon emissions in their public documents. How would you do it?

Let’s say someone hands you a coin that may or may not be unfair. How many times do you need to flip it to confidently determine whether it’s biased towards heads?

Any machine learning practioner will tell you that most of their time isn’t spent building models. Instead, it’s spent obsessing over data. The higher the quality of the information captured in your data, the higher the quality of your resulting model.

A human heart is an astounding machine that is designed to continually function for up to a century without failure. One of the key ways to measure how well your heart is functioning is to compute its ejection fraction: after your heart relaxes at its diastole to fully fill with blood, what percentage does it pump out upon contracting to its systole? The first step of getting at this metric relies on segmenting (delineating the area) of the ventricles from cardiac images.