Learning Principles
Abstract
This chapter is an introduction to fundamental principles of machine learning, where intelligent agents are expected to live in an environment that is described in terms of constraint satisfaction. Beginning from the classic protocol of supervised learning, the notions of loss and risk functions are introduced along with most classic statistical properties. Then the chapter begins driving the reader towards the general approach of constraint-based learning by introducing appropriate penalties to incorporate different types of environmental constraints. Different approaches to learning are discussed that are inspired by statistics, information-based theories, and the parsimony principle. The chapter ...
Get Machine Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
