liveBook · Manning

Linear classifier

As explained in Grokking Machine Learning, Second Edition

A classifier whose decision is determined by a linear function of its inputs.

A linear classifier makes a decision with a linear function of its inputs. In two dimensions, its boundary looks like a line; in higher dimensions, it looks like a plane. Perceptrons are linear classifiers, and neural networks can combine them to produce nonlinear decision boundaries. section 10.0

Two lines for alien happiness

Imagine classifying whether an alien is happy. One linear classifier measures career happiness, while another measures family happiness. An AND operator labels the alien happy only when both classifiers return Yes. Each classifier is represented by a line, making the combined model a step toward a neural network. section 10.3

Figure 10.4 The happiness classifier is formed by the career happiness classifier, the family happiness classifier, and an AND operator. If both the career and family happiness classifiers output a Yes, then so does the happiness classifier. If any of them outputs a No, then the happiness classifier also outputs a No.

Follow the diagram from the two linear happiness classifiers through the AND operator to the final happiness prediction. section 10.3

How Grokking Machine Learning, Second Edition covers it

How deep it goes
Explains geometric boundaries and classifier composition, but stops short of detailed parameter-learning mechanics.
Examples
Uses career happiness, family happiness, two lines, and an AND operator to illustrate combined classification.
What it assumes
Builds on perceptrons and introduces their relationship to neural networks through simple geometric and logical examples.
What you can do after
Evaluate how simple linear classifiers combine into neural networks and yield nonlinear classifiers.
How it connects
Connects linear classifiers with perceptrons, neural networks, nonlinear classifiers, and the AND operator.

Also explained in

Compare how 2 books explain linear classifier →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning, Second Edition. The section links point to the parts of the book it draws on.