6.1.5 LinearizeNet and NeuronDelete

The commands LinearizeNet and NeuronDelete modify the structure of an existing network.

You can linearize an RBF network at any input signal point using LinearizeNet.

Linearize a radial basis function network.

LinearizeNet returns a linear model in the form of a feedforward network without any hidden neurons as described in Section 2.5.1, Feedforward Neural Networks.

The point of the linearization x should be a list of real numbers of length equal to the number of inputs of the neural network.

Sometimes it may be of interest to remove parts of an existing network. NeuronDelete can be used to remove outputs, inputs, hidden neurons, or a linear submodel.

You can also remove individual parameters by setting their numerical values to zero and excluding them from the training, as described in Section 13.2, Fixed Parameters.

Delete the neurons in an existing network.

The argument pos indicates which part of the network should be deleted in the following ways:

{0,0}: removes the linear submodel

{0,m}: removes input m

{1,m}: removes neuron m

{2,m}: removes output m

The argument pos can also be a list where each element follows these rules.

If input data is submitted, then the parameters of the output layer and the linear submodel are adjusted so that the new network approximates the original one as well as possible. The least-squares algorithm is used for this.

There is no adjustment of the parameters if an input or an output is removed.