MATLAB: How to change number of hidden layers with nprtool

"hiddenDeep Learning Toolboxlayerneural networknprtool

Hi, I am designing a neural network using nprtool, and was wondering if there any way to increase the number of hidden layers?

Thanks,

Nika

Best Answer

I don't think the GUI allows multiple hidden layers.

Typically, that is not important because a single hidden layer with enough nodes yields a universal approximator and therefore, is sufficient.

Multiple hidden layers tend to be used only when there is apriori information about the mathematical or physical significance of the underlying I/O relationship or a single hidden layer would require the estimation of too many weights.

Hope this helps.

Thank you for officially accepting my answer.

Greg

Related Solutions

MATLAB: Improve the performance of nprtool

Insufficient information

 Which of the MATLAB classification example datasets are you using?
 help nndatasets
 doc nndatasets
 Number of classes  c =?
 Input vector dimensionality I = 1
 Number of examples  N = ?
 [ I N ] = size(input)
 [ O N ] = size(target)% O = c
 Default 70/15/15 data division? (75/15/15 doesn't add to 100)

Some problems require multiple(e.g., 10) designs for every value of hidden nodes that are tried.

For example, search the NEWSGROUP and ANSWERS using

 greg patternnet Ntrials
 Sorry I can't give you much advice on how to optimize the use of nprtool. However, consulting my command line code should be more than worthwhile.

Hope this helps.

Thank you for formally accepting my answer

Greg.

MATLAB: Layer in neural network

Two of the most important uses for Neural Networks are regression(function approximation, curvefitting) and classification/pattern-recognition.

The best way to design NNs is via the Neural Network Toolbox

In general, the best function to use for regression is FITNET. Start with the help and doc documentation using the command line commands

 help fitnet
 doc fitnet

Next check out some of my posts on the NEWSGROUP and ANSWERS. Search using

 greg fitnet

In general, the best function to use for classification/pattern-recognition is PATTERNNET. Start with the help and doc documentation using the command line commands

 help patternnet
 doc patternnet

Next check out some of my posts on the NEWSGROUP and ANSWERS. Search using

 greg patternnet

Finally, use MATLAB data to practice with

 help nndatasets
 doc nndatasets

If you have problems, it is easier for us to help if you use those datasets.

The help and doc examples use as many default settings as possible. Therefore my best advice for beginners is to begin your designs similarly with one exception. Since by default, the trn/val/tst data division and initial weights are chosen randomly, it is important to know the initial state of the random number generator. The best way to do that is for you to set it to your favorite state before using TRAIN. If designing multiple designs in a loop, initialize RNG before the loop.

 help rng
 doc rng

The default topology is I-H-O ( H=10 default) for I dimensional input vectors and corresponding O-dimensional Output target vectors. The one hidden layer contains H=10 hidden nodes containing tansig (tanh) transfer functions.

The one hidden layer net is a universal approximator. Increasing the number of hidden nodes increases the ability to model more complex functions. However using more than needed decreases the ability to operate well on unseen data. The only reason to use more layers is if you want to decrease the total number of hidden nodes or, to try to model subclasses for classification.

 hiddenLayerSize=200

Replaces the 10 tansig hidden units with 200. Typically, this is a ridiculous number.

 net.divideParam.trainRatio=70/100 
 net.divideParam.valRatio=15/100 
 net.divideParam.testRatio=15/100

Divides the data into training, validation and test subsets with the ratio 70/15/15. However, this is the default ratio. Therefore those statements can be deleted.

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: Improve the performance of nprtool

MATLAB: Layer in neural network

Related Question