Documentation /  Neural Networks /  Training Feedforward and Radial Basis Function Networks /

Further ReadingNeuralFit

7 Training Feedforward and Radial Basis Function Networks

This section describes the training algorithms available for feedforward neural networks (FF networks) and radial basis function networks (RBF networks) using the command NeuralFit. This command is also used for dynamical networks. First, a detailed description of the command is given in Section 7.1, NeuralFit, followed by Section 7.2, Example of Different Training Algorithms. In Section 7.3, Train with FindMinimum, NeuralFit is used to call the built-in command FindMinimum. In Section 7.4 ,Troubleshooting, some possible remedies to frequent problems with the training are presented. Sections 7.5 to 7.8 contain examples on how the options of NeuralFit can be used to change the basic minimization algorithm. In Section 7.9, Writing Your Own Training Algorithms, the commands SetNeuralD and NeuralD are described; they may be useful if you want to develop your own training algorithm for FF and RBF networks.

A short tutorial on the training (or, equivalently, minimization) can be found in Section 2.5.3 Training Feedforward and Radial Basis Function Networks. For a more thorough background on minimization, you can consult the references at the end of the chapter.

Further ReadingNeuralFit


Any questions about topics on this page? Click here to get an individual response.Buy NowMore Information