ABSTRACT

This chapter aims to consider a different approach, which is to use local neurons, where each neuron only responds to inputs in one particular part of the input space. radial basis function (RBF) networks never have more than one layer of non-linear neurons, in contrast to the Multi-layer Perceptron. In the RBF network the activations of the hidden nodes is based on the distance between the current input and the weights. The purpose of the RBF nodes in the hidden layer is to find a non-linear representation of the inputs, while the purpose of the output layer is to find a linear combination of those hidden nodes that does the classification. The most common regulariser that is used for splines is to make the spline model as ‘smooth’ as possible, where the smoothness is measured by computing the second derivative of the curve at each point, squaring it so that it is always positive, and integrating it along the curve.