Neural Network Toolbox Previous page   Next Page

Biases

initFcn

This property defines the function used to initialize the ith layer's bias vector, if the network initialization function is initlay, and the ith layer's initialization function is initwb.

This function can be set to the name of any bias initialization function, including the toolbox functions.

Bias Initialization Functions
initcon
Conscience bias initialization function.
initzero
Zero-weight/bias initialization function.
rands
Symmetric random weight/bias initialization function.

This function is used to calculate an initial bias vector for the ith layer (net.b{i}) when init is called, if the network initialization function (net.initFcn) is initlay, and the ith layer's initialization function (net.layers{i}.initFcn) is initwb.

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

learn

This property defines whether the ith bias vector is to be altered during training and adaption.

It can be set to 0 or 1.

It enables or disables the bias' learning during calls to either adapt or train.

learnFcn

This property defines the function used to update the ith layer's bias vector during training, if the network training function is trainb, trainc, or trainr, or during adaption, if the network adapt function is trains.

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

Learning Functions
learncon
Conscience bias learning function.
learngd
Gradient descent weight/bias learning function.
learngdm
Grad. descent w/momentum weight/bias learning function.
learnp
Perceptron weight/bias learning function.
learnpn
Normalized perceptron weight/bias learning function.
learnwh
Widrow-Hoff weight/bias learning rule.

The learning function updates the ith bias vector (net.b{i}) during calls to train, if the network training function (net.trainFcn) is trainb, trainc, or trainr, or during calls to adapt, if the network adapt function (net.adaptFcn) is trains.

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

Side Effects.   Whenever this property is altered, the biases's learning parameters (net.biases{i}.learnParam) are set to contain the fields and default values of the new function.

learnParam

This property defines the learning parameters and values for the current learning function of the ith layer's bias.

The fields of this property depend on the current learning function (net.biases{i}.learnFcn). Evaluate the above reference to see the fields of the current learning function.

Call help on the current learning function to get a description of what each field means.

size (read-only)

This property defines the size of the ith layer's bias vector.

It is always set to the size of the ith layer (net.layers{i}.size).

userdata

This property provides a place for users to add custom information to the ith layer's bias.

Only one field is predefined. It contains a secret message to all Neural Network Toolbox users.


Previous page  Targets Input Weights Next page

© 1994-2005 The MathWorks, Inc.