The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

Neural network: output model descriptions are wrong?

phivuphivu Member Posts: 34 Maven
edited November 2018 in Help

Hello RapidMiner,

 

I'm using neural network operator to do regression and want to use the output trained model (parameters) for another program in C++. However, after checking the calculations manually using the output trained paramaters, the results do not match with the predicted values by the trained neural network. I tried to search for this problem and found these 2 same questions asked a few years ago:

 

http://community.rapidminer.com/t5/RapidMiner-Studio/What-are-the-calculations-of-a-neural-network-output/m-p/23361#M17331

 

http://community.rapidminer.com/t5/RapidMiner-Studio/Newbie-question-Deriving-formulae-for-Neural-Nets/m-p/16214#M12070

 

So do you have any suggestion to solve my problem? (which is how to use the output trained parameters for another program in C++?)

 

Thank you very much for your help!

 

Best Regards,

Phi Vu

Answers

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,533 RM Data Scientist

    Hi,

     

    did you have a look on the predict code of the neural net on github?

     

    ~Martin

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.