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.
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.
0 Comments