liveBook · Manning

Radial basis function kernel

Also called RBF kernel, Gaussian kernel

A radial basis function kernel is a similarity function whose value depends on the distance between inputs and typically decreases as that distance increases.

How 4 Manning books explain it

Grokking Machine Learning

A kernel based on a radial function whose value depends on the distance between an input point and a center point.

How it is used
Builds nonlinear SVM classifiers when linear boundaries cannot separate the data.
How deep it goes
Explains similarity features, summed radial functions, projected boundaries, and gamma width, without deriving the full kernel mathematics.
Examples
Uses one-dimensional points, two-dimensional triangle-and-square datasets, similarity tables, circular boundaries, and different gamma values.
What you can do after
Apply it via an SVM to classify datasets with complex curved regions.

Read how Grokking Machine Learning explains radial basis function kernel →

Bayesian Optimization in Action

An RBF kernel is a radial basis function covariance or similarity function whose value decreases with distance between inputs according to a length-scale parameter.

How it is used
Uses distance-based covariance to model similarity between inputs in Gaussian processes.
How deep it goes
Explains distance intuition, numerical behavior, GP integration, hyperparameter training, and limitations on structured data.
Examples
Demonstrates covariances for 0 versus 0.1 and 0 versus 10, plus GP modeling of MNIST images.
What you can do after
Build it with GPyTorch by adding an RBFKernel to a GP model and training its hyperparameters with Adam.

Read how Bayesian Optimization in Action explains radial basis function kernel →

Machine Learning Algorithms in Depth

A kernel function whose value typically decreases exponentially with the squared Euclidean distance between its input vectors.

How it is used
Uses RBF similarity in binary SVM classification and as covariance in Gaussian process regression.
How deep it goes
Defines and implements exponential squared-distance kernels; leaves their infinite-dimensional feature-vector equivalence as an exercise.
Examples
Implements a NumPy SVM kernel and a SciPy distance-based Gaussian process kernel for regression.
What you can do after
Build it from scratch as a similarity function for an SVM or a covariance function for Gaussian process regression.

Read how Machine Learning Algorithms in Depth explains radial basis function kernel →

Timeless Algorithms, The Foundational Ideas

A radial basis function kernel is a kernel function whose similarity decreases with distance between observations according to a radial basis function.

How it is used
Uses distance-based comparisons to let support vector machines represent localized nonlinear decision boundaries.
How deep it goes
Defines RBF similarity mathematically and relates γ and C to boundary flexibility, overfitting, and cross-validation-based selection.
Examples
Compares linear, polynomial, and RBF boundaries on the same synthetic two-class data.
What you can do after
Evaluate candidate RBF settings through cross-validation and interpret how γ and C alter boundary flexibility.

Read how Timeless Algorithms, The Foundational Ideas explains radial basis function kernel →

Also covered in

What to know first

Related concepts

Questions about radial basis function kernel

What is radial basis function kernel?

A radial basis function kernel is a similarity function whose value depends on the distance between inputs and typically decreases as that distance increases.

Which Manning books explain radial basis function kernel?

Grokking Machine Learning, Bayesian Optimization in Action, Machine Learning Algorithms in Depth and Timeless Algorithms, The Foundational Ideas.

What should I know before learning radial basis function kernel?

Manning books that teach radial basis function kernel usually introduce accuracy, covariance, linear regression and classifier first.

What is radial basis function kernel a kind of?

Radial basis function kernel is a kind of kernel function. A kernel function is a mathematical function that measures similarity between inputs, often by representing an inner product in an implicit feature space.

What is radial basis function kernel also called?

Radial basis function kernel is also called RBF kernel or Gaussian kernel.

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.