RI Y4 CEP Lesson 12 2022

A Tiny Taste of Machine Learning Lesson 12

The plan ahead • Machine learning is a huge topic – with many tertiary modules dedicated to it • natural language processing, computational biology, computer vision, robotics, other areas • In this class, we will • provide an introduction to the basic ideas, including ways to measure distances between examples, and how to group examples based on distance to create models • introduce classification methods, such as “k nearest neighbor” methods • introduce clustering methods, such as “k-means”

What is Machine Learning • Many useful programs learn something • In last few lessons, we used linear regression to learn models of data • “Field of study that gives computers the ability to learn without being explicitly programmed.” Arthur Samuel • Computer pioneer who wrote first self-learning program, which played checkers – learned from “experience” • invented alpha-beta pruning – widely used in decision tree searching

All ML Methods Require: • Choosing training data and evaluation method • representation of the features • distance metric for feature vectors • objective function and constraints • optimization method for learning the model