Network Object Reference (Neural Network Toolbox)

Neural Network Toolbox

Subobject Structures

These properties consist of cell arrays of structures that define each of the network's inputs, layers, outputs, targets, biases, and weights.

The properties for each kind of subobject are described in the Subobject Properties section that follows this Network Properties section.

inputs

This property holds structures of properties for each of the network's inputs.

```
net.inputs
```

It is always an cell array of input structures, where is the number of network inputs (net.numInputs).

The structure defining the properties of the ith network input is located at:

```
net.inputs{i}
```

Input Properties. See Inputs in the Subobject Properties section for descriptions of input properties.

layers

This property holds structures of properties for each of the network's layers.

```
net.layers
```

It is always an cell array of layer structures, where is the number of network layers (net.numLayers).

The structure defining the properties of the ith layer is located at:

```
net.layers{i}
```

Layer Properties. See Layers in the Subobject Properties section for descriptions of layer properties.

outputs

This property holds structures of properties for each of the network's outputs.

```
net.outputs
```

It is always an cell array, where is the number of network layers (net.numLayers).

The structure defining the properties of the output from the ith layer (or a null matrix []) is located at

```
net.outputs{i}
```

if the corresponding output connection is 1 (or 0).

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

Output Properties. See Outputs in the Subobject Properties section for descriptions of output properties.

targets

This property holds structures of properties for each of the network's targets.

```
net.targets
```

It is always an cell array, where is the number of network layers (net.numLayers).

The structure defining the properties of the target associated with the ith layer (or a null matrix []) is located at

```
net.targets{i}
```

if the corresponding target connection is 1 (or 0).

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

Target Properties. See Targets in the Subobject Properties section for descriptions of target properties.

biases

This property holds structures of properties for each of the network's biases.

```
net.biases
```

It is always an cell array, where is the number of network layers (net.numLayers).

The structure defining the properties of the bias associated with the ith layer (or a null matrix []) is located at

```
net.biases{i}
```

if the corresponding bias connection is 1 (or 0).

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

Bias Properties. See Biases in the Subobject Properties section for descriptions of bias properties.

inputWeights

This property holds structures of properties for each of the network's input weights.

```
net.inputWeights
```

It is always an cell array, where is the number of network layers (net.numLayers), and is the number of network inputs (net.numInputs).

The structure defining the properties of the weight going to the ith layer from the jth input (or a null matrix []) is located at

```
net.inputWeights{i,j}
```

if the corresponding input connection is 1 (or 0).

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

Input Weight Properties. See Input Weights in the Subobject Properties section for descriptions of input weight properties.

layerWeights

This property holds structures of properties for each of the network's layer weights.

```
net.layerWeights
```

It is always an cell array, where is the number of network layers (net.numLayers).

The structure defining the properties of the weight going to the ith layer from the jth layer (or a null matrix []) is located at:

```
net.layerWeights{i,j}
```

if the corresponding layer connection is 1 (or 0).

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

Layer Weight Properties. See Layer Weights in the Subobject Properties section for descriptions of layer weight properties.

Network Object Reference Functions