liveBook · Manning

Sign function

The sign function maps a numeric value to an indicator of whether it is negative, zero, or positive, commonly −1, 0, or 1.

How 2 Manning books explain it

Machine Learning Algorithms in Depth

A sign function returns the sign of a numeric input, commonly mapping positive and negative values to +1 and −1.

How it is used
Maps a perceptron’s linear score to binary predictions for classification.
How deep it goes
Defines the binary mapping and connects it to a hyperplane, without developing the function beyond linear classification.
Examples
Uses a perceptron classifier on the iris dataset and illustrates its two-dimensional decision boundary.
What you can do after
Evaluate a linear score as a binary classification prediction.

Read how Machine Learning Algorithms in Depth explains sign function →

Math and Architectures of Deep Learning

The positive, negative, or zero indicator of a numeric expression, used here to determine which side of a decision boundary a point lies on.

How it is used
Determines which side of a binary-classification decision boundary contains an input point.
How deep it goes
Defines negative, zero, and positive values geometrically, extending from lines to higher-dimensional surfaces.
Examples
Uses the line y + 2x + 1 = 0 and classifier planes to interpret point locations.
What you can do after
Evaluate a surface function’s sign to predict a binary class for an input vector.

Read how Math and Architectures of Deep Learning explains sign function →

Also covered in

Related concepts

Questions about sign function

What is sign function?

The sign function maps a numeric value to an indicator of whether it is negative, zero, or positive, commonly −1, 0, or 1.

Which Manning books explain sign function?

Machine Learning Algorithms in Depth and Math and Architectures of Deep Learning.

What is the difference between sign function and sign bit?

The sign function maps a numeric value to an indicator of whether it is negative, zero, or positive, commonly −1, 0, or 1. A sign bit is a designated bit in a numeric representation that indicates whether the represented value is negative or nonnegative.

What is sign function part of?

Sign function is part of floating-point arithmetic. Floating-point arithmetic is numerical computation using finite-precision representations of real numbers, which can introduce rounding and range errors.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.