In Neural Network Toolbox, how can I can change the values of training Parameters ?

32 visualizzazioni (ultimi 30 giorni)
For example, in the example "Iris Flowers" dataset in "Neural Net Pattern Recognition" App,default training function is trainscg.I want to use another training function which will use learning rate, lr, and momentum constant, mc.Also i want to change values of learning rate, lr, and momentum constant parameters.

Risposta accettata

mizuki il 7 Nov 2016
You cannot customize a lot with App. If you want to train not with default values, change values/parameters on code.
After the training on Neural Pattern Recognition App, click Next until getting to the Save Results page.
Click "Simple Script."
When you want to use the training function that uses learning rate and momentum, use traingdx. (If it is only learning rate, use traingda; if it is only momentum, use traingdm)
In the generated script, there is a line defining the training function such as:
>> trainFcn = 'trainscg';
Change this to, for example:
>> trainFcn = 'traingdx';
If you want to change the parameter of learning rate to 0.1 for example, add
>> = 0.1;
after making the default network, which is the line include PATTERNNET as well as before TRAIN. You can also change the momentum by changing
  2 Commenti
NN il 27 Ott 2020
Hi, i also have the same issue, getting high error .So i tried the above method.but i am getting the error when i changed trainlm to traindx.
Error using fitnet (line 73)
FCN is not the name of a function on the MATLAB path.
kindly advice

Accedi per commentare.

Più risposte (2)

mizuki il 7 Nov 2016
How about using
>> net = patternnet(hiddenLayerSize, trainFcn);
instead of
>> net = patternnet(hiddenLayerSize);
  1 Commento
Machine Learning Enthusiast
works like a charm.Thanks to you. what would be the ideal values for Learning rate and momentum while training data? Should we select randomly to check the best fit ?

Accedi per commentare.

Greg Heath
Greg Heath il 9 Nov 2016
1. Another way to do it is
net = patternnet(hiddenlayersize);
. . .
net.trainFcn = 'traingdx';
[ net tr y e ] = train(net,x,t);
Hope this helps.
Thank you for formally accepting my answer
  2 Commenti
Greg Heath
Greg Heath il 10 Nov 2016
Typically, I have always relied on default values except
1. No of hidden nodes
2. Fixed initial weights
3. MSE goal (I use either 1% (fitnet/patternnet) or 0.1% (timeseries) of the average biased target variance
MSE00 = mean(var(target',1))
In particular, I have not found it necessary to change either learning or momentum.
Hope this helps.
Thank you for formally accepting my answer

Accedi per commentare.


Scopri di più su Sequence and Numeric Feature Data Workflows in Help Center e File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by