Functions :: Network Object Reference (Neural Network Toolbox)

Neural Network Toolbox

Functions

These properties define the algorithms to use when a network is to adapt, is to be initialized, is to have its performance measured, or is to be trained.

adaptFcn

This property defines the function to be used when the network adapts.

```
net.adaptFcn
```

It can be set to the name of any network adapt function, including this toolbox function:

trains - By-weight-and-bias network adaption function.

The network adapt function is used to perform adaption whenever adapt is called.

```
[net,Y,E,Pf,Af] = adapt(NET,P,T,Pi,Ai)
```

Custom Functions.. See Advanced Topics for information on creating custom adapt functions.

Side Effects.. Whenever this property is altered, the network's adaption parameters (net.adaptParam) are set to contain the parameters and default values of the new function.

initFcn

This property defines the function used to initialize the network's weight matrices and bias vectors.

```
net.initFcn
```

It can be set to the name of any network initialization function, including this toolbox function.

initlay  - Layer-by-layer network initialization function.

The initialization function is used to initialize the network whenever init is called.

```
net = init(net)
```

Custom Functions.. See Advanced Topics for information on creating custom initialization functions.

Side Effects.. Whenever this property is altered, the network's initialization parameters (net.initParam) are set to contain the parameters and default values of the new function.

performFcn

This property defines the function used to measure the network's performance.

```
net.performFcn
```

It can be set to the name of any performance function, including these toolbox functions.

Performance Functions

mae
Mean absolute error-performance function.

mse
Mean squared error-performance function.

msereg
Mean squared error w/reg performance function.

sse
Sum squared error-performance function.

Performance Functions
`mae`	Mean absolute error-performance function.
`mse`	Mean squared error-performance function.
`msereg`	Mean squared error w/reg performance function.
`sse`	Sum squared error-performance function.

The performance function is used to calculate network performance during training whenever train is called.

```
[net,tr] = train(NET,P,T,Pi,Ai)
```

Custom functions.. See Advanced Topics for information on creating custom performance functions.

Side Effects.. Whenever this property is altered, the network's performance parameters (net.performParam) are set to contain the parameters and default values of the new function.

trainFcn

This property defines the function used to train the network.

```
net.trainFcn
```

It can be set to the name of any training function, including these toolbox functions.

Training Functions

trainbfg
BFGS quasi-Newton backpropagation.

trainbr
Bayesian regularization.

traincgb
Powell-Beale conjugate gradient backpropagation.

traincgf
Fletcher-Powell conjugate gradient backpropagation.

traincgp
Polak-Ribiere conjugate gradient backpropagation.

traingd
Gradient descent backpropagation.

traingda
Gradient descent with adaptive lr backpropagation.

traingdm
Gradient descent with momentum backpropagation.

traingdx
Gradient descent with momentum and adaptive lr backpropagation

trainlm
Levenberg-Marquardt backpropagation.

trainoss
One-step secant backpropagation.

trainrp
Resilient backpropagation (Rprop).

trainscg
Scaled conjugate gradient backpropagation.

trainb
Batch training with weight and bias learning rules.

trainc
Cyclical order incremental training with learning functions.

trainr
Random order incremental training with learning functions.

Training Functions
`trainbfg`	BFGS quasi-Newton backpropagation.
`trainbr`	Bayesian regularization.
`traincgb`	Powell-Beale conjugate gradient backpropagation.
`traincgf`	Fletcher-Powell conjugate gradient backpropagation.
`traincgp`	Polak-Ribiere conjugate gradient backpropagation.
`traingd`	Gradient descent backpropagation.
`traingda`	Gradient descent with adaptive lr backpropagation.
`traingdm`	Gradient descent with momentum backpropagation.
`traingdx`	Gradient descent with momentum and adaptive lr backpropagation
`trainlm`	Levenberg-Marquardt backpropagation.
`trainoss`	One-step secant backpropagation.
`trainrp`	Resilient backpropagation (Rprop).
`trainscg`	Scaled conjugate gradient backpropagation.
`trainb`	Batch training with weight and bias learning rules.
`trainc`	Cyclical order incremental training with learning functions.
`trainr`	Random order incremental training with learning functions.

The training function is used to train the network whenever train is called.

```
[net,tr] = train(NET,P,T,Pi,Ai)
```

Custom Functions.. See Advanced Topics for information on creating custom training functions.

Side Effects.. Whenever this property is altered, the network's training parameters (net.trainParam) are set to contain the parameters and default values of the new function.

Subobject Structures Parameters