Machine Learning for Everyone: Introduction to Classification and Clustering

Summary This Novel AI assignment module introduces two important machine learning approaches: Classification and Clustering. Each approach provides a way to group things together, the key difference being whether or not the groupings to be made are decided ahead of time. While these grouping techniques are a type of Artificial Intelligence designed to be performed by a computer, they can be used on any sort of data from any discipline. The module provides background for an instructor in any discipline to incorporate the material into a lesson for students in any discipline where machine learning may be applicable. It is aimed at a beginner, non-technical student audience, though it is also appropriate as an introduction for students with some computing experience. Materials for hands-on exercises and pre- and post-test quizzes are included.
Topics Machine Learning, Artificial Intelligence, Supervised Learning, Unsupervised Learning, Classification, Clustering
Audience Undergraduate college students in any discipline where exposure to introductory machine learning concepts may be beneficial. Also appropriate for college majors in a computing discipline as a first introduction to applications of machine learning. May also be suitable for high school students.
Difficulty Beginner level, very accessible material requiring up to one typical class meeting or lecture period.
Strengths Use of unplugged activities, pencil and paper activities, intuitive introduction to machine learning understandable by non-technical students, introduces applicablility to many other disciplines, no computers required, usable by instructors in any discipline as it requires no in-depth background in the topics covered.
Weaknesses Not scalable to class sizes over 30, does not discuss mathematical underpinnings of concepts presented.
Dependencies No specific pre-requisite knowledge needed, although coverage of our related "Introduction to Machine Learning" module is beneficial though not necessary.
Variants Instructors in many other disciplines, including non-computing disciplines, can follow ideas in material to apply Classification and Clustering techniques into those disciplines and generate student interest in applications of machine learning to their own discipline. Instructors can customize activities and create relevant assignments that build on concepts presented using data and examples from their own disciplines as described in provided material.

Assignment Materials