The Math Forum

Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Math Forum » Discussions » Software » comp.soft-sys.matlab

Topic: Neural Networks weights and bias help
Replies: 18   Last Post: Jan 22, 2016 9:11 AM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View   Messages: [ Previous | Next ]
Murugan Solaiyappan

Posts: 53
Registered: 12/4/10
Re: Neural Networks weights and bias help
Posted: Dec 20, 2012 4:54 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

> What EXACTLY do you want to do?

I have one year of stock data.
My 12 input is fuzzified data
My 12 output also fuzzified data.
I want to compare the result from original data with neural network result. and also i want to predict the stock data.

> What version of MATLAB do you have?
Matlab version: MATLAB Version (R2010a)
> Please post the documentation you get from the command
> help newff

NEWFF Create a feed-forward backpropagation network.


net = newff(P,T,S,TF,BTF,BLF,PF,IPF,OPF,DDF)


P - RxQ1 matrix of Q1 representative R-element input vectors.
T - SNxQ2 matrix of Q2 representative SN-element target vectors.
Si - Sizes of N-1 hidden layers, S1 to S(N-1), default = [].
(Output layer size SN is determined from T.)
TFi - Transfer function of ith layer. Default is 'tansig' for
hidden layers, and 'purelin' for output layer.
BTF - Backprop network training function, default = 'trainlm'.
BLF - Backprop weight/bias learning function, default = 'learngdm'.
PF - Performance function, default = 'mse'.
IPF - Row cell array of input processing functions.
Default is {'fixunknowns','removeconstantrows','mapminmax'}.
OPF - Row cell array of output processing functions.
Default is {'removeconstantrows','mapminmax'}.
DDF - Data division function, default = 'dividerand';
and returns an N layer feed-forward backprop network.

The transfer functions TF{i} can be any differentiable transfer
function such as TANSIG, LOGSIG, or PURELIN.

The training function BTF can be any of the backprop training
functions such as TRAINLM, TRAINBFG, TRAINRP, TRAINGD, etc.

*WARNING*: TRAINLM is the default training function because it
is very fast, but it requires a lot of memory to run. If you get
an "out-of-memory" error when training try doing one of these:

(1) Slow TRAINLM training, but reduce memory requirements, by
setting NET.trainParam.mem_reduc to 2 or more. (See HELP TRAINLM.)
(2) Use TRAINBFG, which is slower but more memory efficient than TRAINLM.
(3) Use TRAINRP which is slower but more memory efficient than TRAINBFG.

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.


load simplefit_dataset
net = newff(simplefitInputs,simplefitTargets,20);
net = train(net,simplefitInputs,simplefitTargets);
simplefitOutputs = sim(net,simplefitInputs);


Feed-forward networks consist 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
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 newcf, newelm, sim, init, adapt, train, trains

Reference page in Help browser
doc newff
> Greg

Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© The Math Forum at NCTM 1994-2017. All Rights Reserved.