MATLAB: Neural Network Results Are Not Close To Test Data

custom neural networkDeep Learning Toolboxprediction

I am using 2 layer 'trainlm' custom neural network and layers transfer functions are 'tansig' however when I get results are not close to test data. It is looking like attached pic. Do you have any idea?

Best Answer

Yes. You've made at least one mistake.

Related Solutions

MATLAB: Testing neural network’s forecasting ability

Your code works on the dataset in the documentation

 help narnet
 doc  narnet

However, I did not try it on any of the other NARNET example datasets:

 help nndatasets
 doc nndatasets

I can only quote my general approach :

a. Test code on one or more a MATLAB example datasets
b. Use your data to obtain the best openloop performance of multiple (>=10) designs
c. If closing the loop sufficiently degrades performance, then train netc.

Hope this helps

Thank you for formally accepting my answer

Greg

MATLAB: Close all training progress plot

Hi,

As mentioned in this MATLAB Question you may use

delete(findall(0));

for closing all the opened training progress plots because the ‘HandleVisibility’ is set to ‘off’ for these plots by default.

Hope it helps.

Best Answer

Related Solutions

MATLAB: Testing neural network’s forecasting ability

MATLAB: Close all training progress plot

Related Question