Neural Network Toolbox User's Guide

Network ArchitecturesYou can create a single (composite) layer of neurons having different transferfunctions simply by putting two of the networks shown earlier in parallel. Bothnetworks would have the same inputs, and each network would create some ofthe outputs.The input vector elements enter the network through the weight matrix W.w 1, 1 w 1, 2 … w 1,RW=w 2, 1 w 2, 2 … w 2,Rw S, 1 w S, 2 … w S,RNote that the row indices on the elements of matrix W indicate the destinationneuron of the weight, and the column indices indicate which source is the inputfor that weight. Thus, the indices in w 1, 2 say that the strength of the signalfrom the second input element to the first (and only) neuron is w 1,2 .The S neuron R input one-layer network also can be drawn in abbreviatednotation.Input Layer of NeuronspWR x 1S x R faS x 1nS x 11 b RS x 1S a= f (Wp + b)Where...R = number ofelements ininput vectorS = number ofneurons in layer 1Here p is an R length input vector, W is an SxR matrix, and a and b are Slength vectors. As defined previously, the neuron layer includes the weightmatrix, the multiplication operations, the bias vector b, the summer, and thetransfer function boxes.2-9