Letter #14 - In which we conveniently pretend that letter 13 was thing.
“Make the important interesting.”
Save me from drowning in the sea
Beat me up on the beach
What a lovely holiday, there’s nothing funny left to say
A model that is overly-simplistic is just as problematic as one that is overly-scrupulous. Errors due to bias and those due to variance are distinct. Understanding the tradeoff between bias and variance (and how different model types let you balance the two) is foundational to modeling well.
#ohmygod part 2 is here! Along with part one this is it’s one of the nicest explanations of trees in general and of the bias/variance thingie in particular that I’ve seen. Not to mention the visualizations are just so…visual.
Seeing Theory is a project designed and created by Daniel Kunin with support from Brown University’s Royce Fellowship Program. The goal of the project is to make statistics more accessible to a wider range of students through interactive visualizations.
Since we’re talking about seeing, you should also take a look at this experiment. While not technically about machine learning, it’ll help you understand some of the statistics and probability concepts needed for ml. Plus, it’s really fun to play with.
Not sure what you just read? Take a look at this post.
Enjoyed it? Subscribe to my tiny newsletter and get new issues straight to your inbox. Every week, on Tuesdays.