matlab神经网络训练准确率,Matlab神经网络 训练数据量的多少对训练误差的影响...

版本不一样 所以描述的也不同 2007市这样的

help newelm

NEWELM Create an Elman backpropagation network.

Syntax

net = newelm

net = newelm(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)

Description

NET = NEWELM creates a new network with a dialog box.

NET = NEWELM(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF) takes several arguments,

PR  - Rx2 matrix of min and max values for R input elements.

Si  - Size of ith layer, for Nl layers.

TFi - Transfer function of ith layer, default = 'tansig'.

BTF - Backprop network training function, default = 'traingdx'.

BLF - Backprop weight/bias learning function, default = 'learngdm'.

PF  - Performance function, default = 'mse'.

and returns an Elman network.

The training function BTF can be any of the backprop training

functions such as TRAINGD, TRAINGDM, TRAINGDA, TRAINGDX, etc.

*WARNING*: Algorithms which take large step sizes, such as TRAINLM,

and TRAINRP, etc., are not recommended for Elman networks.  Because

of the delays in Elman networks the gradient of performance used

by these algorithms is only approximated making learning difficult

for large step algorithms.

The learning function BLF can be either of the backpropagation

learning functions such as 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

which is 1 wherever P has had two 1's in a row.

P = round(rand(1,20));

T = [0 (P(1:end-1)+P(2:end) == 2)];

We would like the network to recognize whenever two 1's

occur in a row.  First we arrange these values as sequences.

Pseq = con2seq(P);

Tseq = con2seq(T);

Next we create an Elman network whose input varies from 0 to 1,

and has five hidden neurons and 1 output.

net = newelm([0 1],[10 1],{'tansig','logsig'});

Then we 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

Elman 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

Reference page in Help browser

doc newelm