calcpd (Neural Network Toolbox)

Neural Network Toolbox

calcpd

Calculate delayed network inputs

Syntax

Pd = calcpd(net,TS,Q,Pc)

Description

This function calculates the results of passing the network inputs through each input weights tap delay line.

Pd = calcpd(net,TS,Q,Pc) takes,

net -- Neural network

TS -- Time steps

Q -- Concurrent size

Pc -- Combined inputs = [initial delay conditions, network inputs]

and returns,

Pd -- Delayed inputs

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.

```
net = newlin([0 1],3,[0 2 4]);
```

Here is a single (Q = 1) input sequence P with eight time steps (TS = 8).

```
P = {0 0.1 0.3 0.6 0.4 0.7 0.2 0.1};
```

Here we define the four initial input delay conditions Pi.

```
Pi = {0.2 0.3 0.4 0.1};
```

The delayed inputs (the inputs after passing through the tap delays) can be calculated with calcpd.

```
Pc = [Pi P];
Pd = calcpd(net,8,1,Pc)
```

Here we view the delayed inputs for input weight going to layer 1, from input 1 at time steps 1 and 2.

```
Pd{1,1,1}
Pd{1,1,2}
```

calcjx calcperf