Model Families

Once the problem shape and the learning setting are known, the remaining choice is which algorithm family to reach for. The page gives a map from task type to algorithm family first, then a course-level reference behind it.

The same notes are in Meta Learning.

The map is SAS's "Which machine learning algorithm should I use?", designed primarily for beginner to intermediate data scientists or analysts who want to identify and apply machine learning algorithms to their own problems: A wonderful introduction into machine learning, and how to choose the right algorithm or family of algorithms for the task at hand.

Behind the map sits the course material: Stanford cs221 is the CS 221 teaching page.