newlrn

Purpose

Create layered-recurrent network

Syntax

• net = newlrn(P,T,[S1 S2...S(N-l)],{TF1 TF2...TFNl}, 
  BTF,BLF,PF,IPF,OPF,DDF)
  

Description

net = newlrn(P,T,[S1 S2...S(N-l)],{TF1 TF2...TFNl}, BTF,BLF,PF,IPF,OPF,DDF) takes several arguments,

P	R x Q1 matrix of Q1 sample R-element input vectors
T	SN x Q2 matrix of Q2 sample SN-element input vectors
Si	Size of ith layer, for N-1 layers, default = [ ]. (Output layer size SN is determined from T.)
TFi	Transfer function of ith layer. (Default = 'tansig' for hidden layers and 'purelin' for output layer.)
BTF	Backpropagation network training function (default = 'trainlm')
BLF	Backpropagation weight/bias learning function (default = 'learngdm')
PF	Performance function (default = 'mse')
IPF	Row cell array of input processing functions. (Default = {'fixunknowns','removeconstantrows','mapminmax'})
OPF	Row cell array of output processing functions. (Default = {'removeconstantrows','mapminmax'})
DDF	Data divison function (default = 'dividerand')

and returns a layered-recurrent network.

The training function BTF can be any of the backpropagation training functions such as trainlm, trainbfg, trainscg, trainbr, etc.

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.

Examples

Here is a series of Boolean inputs P and another sequence T that is 1 whenever P has two 1s in a row.

• P = round(rand(1,20));
  T = [0 (P(1:end-1)+P(2:end) == 2)];
  

You want the network to recognize whenever two 1s occur in a row. First arrange these values as sequences.

• Pseq = con2seq(P);
  Tseq = con2seq(T);
  

Next create a layered-recurrent network with one hidden layer of ten neurons.

• net = newlrn(P,T,10);
  

Then train the network with a mean squared error goal of 0.1 and simulate it.

• net = train(net,Pseq,Tseq);
  Y = sim(net,Pseq)
  

Algorithm

Layered-recurrent networks consists of Nl layers using the dotprod weight function, netsum net input function, and the specified transfer functions.

The first layer has weights coming from the input. Each subsequent layer has a weight coming from the previous layer. All layers except the last have a recurrent weight. All layers have biases. The last layer is the network output.

Each layer's weights and biases are initialized with initnw.

Adaption is done with trains, which updates weights with the specified learning function. Training is done with the specified training function. Performance is measured according to the specified performance function.

See Also

newff, newcf, sim, init, adapt, train, trains

Provide feedback about this page

newlind

newlvq

© 1984-2009- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS