liveBook · Manning

Decision function

As explained in Timeless Algorithms, The Foundational Ideas

A decision function is a mathematical function that assigns a score to an input for determining its predicted class.

A decision function assigns a numerical score to a feature vector. For a linear classifier, the score combines feature values with weights and a bias; its sign determines the predicted class. section 8.2.1

f(x)=wTx+b

The weights determine how features contribute to the score, while the bias shifts the decision boundary. section 8.2.1

Scoring two points

With f(x)=2x₁−x₂−3, the point (3, 1) scores 2 and receives class +1; (1, 4) scores −5 and receives class −1. The assignment of labels to real-world classes is arbitrary, provided it stays consistent. section 8.2.1

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Explains the linear score, parameter geometry, sign rule, and worked evaluations, then leaves boundary optimization to the maximum-margin treatment.
Examples
Evaluates two feature vectors with a specified linear function and maps positive and negative scores to classes.
What you can do after
Evaluate a feature vector by computing its score and using the sign to determine its predicted class.
How it connects
Connects the score to hyperplanes, weights, bias, margins, and support vectors in support vector machines.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Timeless Algorithms, The Foundational Ideas. The section links point to the parts of the book it draws on.