Neural Network Toolbox™

Update NNT 2.0 Elman backpropagation network

Syntax

• net = nnt2elm(PR,W1,B1,W2,B2,BTF,BLF,PF)
  

Description

nnt2elm(PR,W1,B1,W2,B2,BTF,BLF,PF) takes these arguments,

PR	R x 2 matrix of min and max values for R input elements
W1	S1 x (R+S1) weight matrix
B1	S1 x 1 bias vector
W2	S2 x S1 weight matrix
B2	S2 x 1 bias vector
BTF	Backpropagation network training function (default = 'traingdx')
BLF	Backpropagation weight/bias learning function (default = 'learngdm')
PF	Performance function (default = 'mse')

and returns a feed-forward network.

The training function BTF can be any of the backpropagation training functions such as traingd, traingdm, traingda, or traingdx. Large step-size algorithms, such as trainlm, are not recommended for Elman networks.

The learning function BLF can be either of the backpropagation learning functions learngd or learngdm.

The performance function can be any of the differentiable performance functions such as mse or msereg.

Once a network has been updated, it can be simulated, initialized, adapted, or trained with sim, init, adapt, or train.

See Also

newelm

Provide feedback about this page

nnt2c

nnt2ff

© 1984-2008- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS