Radial Basis Function Network

What Does Radial Basis Function Network Mean?

A radial basis function network is a type of supervised artificial neural network that uses supervised machine learning (ML) to function as a nonlinear classifier. Nonlinear classifiers use sophisticated functions to go further in analysis than simple linear classifiers that work on lower-dimensional vectors.


A radial basis function network is also known as a radial basis network.

Techopedia Explains Radial Basis Function Network

Using a set of prototypes along with other training examples, neurons look at the distance between an input and a prototype, using what is called an input vector.

The activation functions of artificial neurons drive outputs that can be represented in different ways to show how the network classifies data points. The radial basis function network uses radial basis functions as its activation functions. Like other kinds of neural networks, radial basis function networks have input layers, hidden layers and output layers. However, radial basis function networks often also include a nonlinear activation function of some kind. Output weights can be trained using gradient descent. Some consider an RBF approach to be relatively "intuitive" and a good way to address specialized ML problems.


Related Terms

Margaret Rouse
Technology Expert

Margaret is an award-winning technical writer and teacher known for her ability to explain complex technical subjects to a non-technical business audience. Over the past twenty years, her IT definitions have been published by Que in an encyclopedia of technology terms and cited in articles by the New York Times, Time Magazine, USA Today, ZDNet, PC Magazine, and Discovery Magazine. She joined Techopedia in 2011. Margaret's idea of a fun day is helping IT and business professionals learn to speak each other’s highly specialized languages.