Linear Threshold Machines
Abstract
One of the simplest ways of modeling the interactions of intelligent agents with the environment is to expose them to a collection of supervised pairs (example, target). This chapter is about the learning mechanisms that arise from the assumption of dealing with linear and linear-threshold machines. In most cases, the covered topics nicely intercept different disciplines, and are of remarkable importance to better grasp many approaches to machine learning. The chapter covers classic topics, like normal equations and ridge regression, as well as representational issues in pattern recognition that are connected with the notion of predicate order. Linear-threshold machines are described along with ...
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.
