12.07.2015 Views

Neural Network Toolbox User's Guide

Neural Network Toolbox User's Guide

Neural Network Toolbox User's Guide

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Data StructuresData StructuresThis section discusses how the format of input data structures affects thesimulation of networks. We will begin with static networks, and then move todynamic networks.We are concerned with two basic types of input vectors: those that occurconcurrently (at the same time, or in no particular time sequence), and thosethat occur sequentially in time. For concurrent vectors, the order is notimportant, and if we had a number of networks running in parallel, we couldpresent one input vector to each of the networks. For sequential vectors, theorder in which the vectors appear is important.Simulation With Concurrent Inputs in a Static<strong>Network</strong>The simplest situation for simulating a network occurs when the network to besimulated is static (has no feedback or delays). In this case, we do not have tobe concerned about whether or not the input vectors occur in a particular timesequence, so we can treat the inputs as concurrent. In addition, we make theproblem even simpler by assuming that the network has only one input vector.Use the following network as an example.InputsLinear Neuronp w11,1n ap2 wb1,2 1a = purelin (Wp + b)To set up this feedforward network, we can use the following command.net = newlin([1 3;1 3],1);For simplicity assign the weight matrix and bias to be2-13

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!