Network Properties :: Network Object Reference (Neural Network Toolbox)

Neural Network Toolbox

Network Properties

The properties define the basic features of a network. Subobject Properties describes properties that define network details.

Architecture

These properties determine the number of network subobjects (which include inputs, layers, outputs, targets, biases, and weights), and how they are connected.

numInputs

This property defines the number of inputs a network receives.

```
net.numInputs
```

It can be set to 0 or a positive integer.

Clarification. The number of network inputs and the size of a network input are not the same thing. The number of inputs defines how many sets of vectors the network receives as input. The size of each input (i.e. the number of elements in each input vector) is determined by the input size (net.inputs{i}.size).

Most networks have only one input, whose size is determined by the problem.

Side Effects. Any change to this property results in a change in the size of the matrix defining connections to layers from inputs, (net.inputConnect) and the size of the cell array of input subobjects (net.inputs).

numLayers

This property defines the number of layers a network has.

```
net.numLayers
```

It can be set to 0 or a positive integer.

Side Effects. Any change to this property changes the size of each of these Boolean matrices that define connections to and from layers,

net.biasConnect
net.inputConnect
net.layerConnect
net.outputConnect
net.targetConnect

and changes the size each cell array of subobject structures whose size depends on the number of layers,

net.biases
net.inputWeights
net.layerWeights
net.outputs
net.targets

and also changes the size of each of the network's adjustable parameters properties.

```
net.IW
net.LW
net.b
```

biasConnect

This property defines which layers have biases.

```
net.biasConnect
```

It can be set to any N-by-1 matrix of Boolean values, where is the number of network layers (net.numLayers). The presence (or absence) of a bias to the ith layer is indicated by a 1 (or 0) at:

```
net.biasConnect(i)
```

Side Effects. Any change to this property alters the presence or absence of structures in the cell array of biases (net.biases) and, in the presence or absence of vectors in the cell array, of bias vectors (net.b).

inputConnect

This property defines which layers have weights coming from inputs.

```
net.inputConnect
```

It can be set to any matrix of Boolean values, where is the number of network layers (net.numLayers), and is the number of network inputs (net.numInputs). The presence (or absence) of a weight going to the ith layer from the jth input is indicated by a 1 (or 0) at

```
net.inputConnect(i,j)
```

Side Effects. Any change to this property will alter the presence or absence of structures in the cell array of input weight subobjects (net.inputWeights) and in the presence or absence of matrices in the cell array of input weight matrices (net.IW).

layerConnect

This property defines which layers have weights coming from other layers.

```
net.layerConnect
```

It can be set to any matrix of Boolean values, where is the number of network layers (net.numLayers). The presence (or absence) of a weight going to the ith layer from the jth layer is indicated by a 1 (or 0) at

```
net.layerConnect(i,j)
```

Side Effects. Any change to this property will alter the presence or absence of structures in the cell array of layer weight subobjects (net.layerWeights) and in the presence or absence of matrices in the cell array of layer weight matrices (net.LW).

outputConnect

This property defines which layers generate network outputs.

```
net.outputConnect
```

It can be set to any matrix of Boolean values, where is the number of network layers (net.numLayers). The presence (or absence) of a network output from the ith layer is indicated by a 1 (or 0) at

```
net.outputConnect(i)
```

Side Effects. Any change to this property will alter the number of network outputs (net.numOutputs) and the presence or absence of structures in the cell array of output subobjects (net.outputs).

targetConnect

This property defines which layers have associated targets.

```
net.targetConnect
```

It can be set to any matrix of Boolean values, where is the number of network layers (net.numLayers). The presence (or absence) of a target associated with the ith layer is indicated by a 1 (or 0) at

```
net.targetConnect(i)
```

Side Effects. Any change to this property alters the number of network targets (net.numTargets) and the presence or absence of structures in the cell array of target subobjects (net.targets).

numOutputs (read-only)

This property indicates how many outputs the network has.

```
net.numOutputs
```

It is always set to the number of 1's in the matrix of output connections.

```
numOutputs = sum(net.outputConnect)
```

numTargets (read-only)

This property indicates how many targets the network has.

```
net.numTargets
```

It is always set to the number of 1's in the matrix of target connections.

```
numTargets = sum(net.targetConnect)
```

numInputDelays (read-only)

This property indicates the number of time steps of past inputs that must be supplied to simulate the network.

```
net.numInputDelays
```

It is always set to the maximum delay value associated any of the network's input weights.

numInputDelays = 0;
for i=1:net.numLayers
  for j=1:net.numInputs
    if net.inputConnect(i,j)
      numInputDelays = max( ...
        [numInputDelays net.inputWeights{i,j}.delays]);
    end
  end
end

numLayerDelays (read-only)

This property indicates the number of time steps of past layer outputs that must be supplied to simulate the network.

```
net.numLayerDelays
```

It is always set to the maximum delay value associated with any of the network's layer weights.

numLayerDelays = 0;
for i=1:net.numLayers
  for j=1:net.numLayers
    if net.layerConnect(i,j)
      numLayerDelays = max( ...
       [numLayerDelays net.layerWeights{i,j}.delays]);
    end
  end
end

Network Object Reference Subobject Structures