calca1 (Neural Network Toolbox)

Calculate network signals for one time step

Syntax

[Ac,N,LWZ,IWZ,BZ] = calca1(net,Pd,Ai,Q)

Description

This function calculates the outputs of each layer in response to a network's delayed inputs and initial layer delay conditions, for a single time step.

Calculating outputs for a single time step is useful for sequential iterative algorithms such as trains, which need to calculate the network response for each time step individually.

[Ac,N,LWZ,IWZ,BZ] = calca1(net,Pd,Ai,Q) takes,

   net -- Neural network

   Pd -- Delayed inputs for a single time step

    Ai -- Initial layer delay conditions for a single time step

    Q -- Concurrent size

and returns,

    A -- Layer outputs for the time step

    N -- Net inputs for the time step

    LWZ -- Weighted layer outputs for the time step

    IWZ -- Weighted inputs for the time step

    BZ -- Concurrent biases for the time step

Examples

Here we create a linear network with a single input element ranging from 0 to 1, three neurons, and a tap delay on the input with taps at zero, two, and four time steps. The network is also given a recurrent connection from layer 1 to itself with tap delays of [1 2].

net = newlin([0 1],3,[0 2 4]);
net.layerConnect(1,1) = 1;
net.layerWeights{1,1}.delays = [1 2];

Here is a single (Q = 1) input sequence P with eight time steps (TS = 8), and the four initial input delay conditions Pi, combined inputs Pc, and delayed inputs Pd.

P = {0 0.1 0.3 0.6 0.4 0.7 0.2 0.1};
Pi = {0.2 0.3 0.4 0.1};
Pc = [Pi P];
Pd = calcpd(net,8,1,Pc)

Here the two initial layer delay conditions for each of the three neurons are defined:

Ai = {[0.5; 0.1; 0.2] [0.6; 0.5; 0.2]};

Here we calculate the network's combined outputs Ac, and other signals described above.

[Ac,N,LWZ,IWZ,BZ] = calca(net,Pd,Ai,1,8)

calca calce