🦉 🎤   RapidMiner Wisdom 2020 - CALL FOR SPEAKERS   🦉 🎤

We are inviting all community members to submit proposals to speak at Wisdom 2020 in Boston.


Whether it's a cool RapidMiner trick or a use case implementation, we want to see what you have.
Form link is below and deadline for submissions is November 15. See you in Boston!

CLICK HERE TO GO TO ENTRY FORM

Optimize Parameters for Keras Model?

LuatNVLuatNV Member Posts: 1 Newbie
edited January 16 in Help
Dear guys,

I am a newbie in Rapid Miner... Could you please show me any way to optimize parameters of Keras Model (Keras extension)?

Any answer would be appreciated,...

Thank you a lots

Answers

  • sgenzersgenzer 12Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,519  Community Manager
    hi @LuatNV sorry no one has chimed in here. Is this still a problem?
    ----------------------
    Don't forget to submit your great ideas for Wisdom 2020! Deadline is November 15.

    Wisdom 2020 – Call for Speakers Form 

  • M_MartinM_Martin RapidMiner Certified Analyst, Member Posts: 117   Unicorn
    Hi LuatNV: Though I've never done this with the Keras operator, in theory you should be able to use one of the Various "Optimize Parameters" operators - such as "Optimize Parameters Grid"  - which is ussualy a good place to start.  This operator provides a dialog that lets you specify which parameter(s) within what operator(s) you want to optimize and provide starting and ending parameter values to test.  This operator outputs information that gives you the optimal settings for the parameters you chose to optimize.  Bear in mind that depending on how many parameters you want to  optimize, and the spread of starting and ending values, and the number of data rows, your process may require quite some time to run.  A way to get around very long run times is to use a sample of your data on the assumption that a sample of between 25% - 50% is in the majority cases representative of the range of values you would see in your complete data set.  Hope this helps and best wishes, Michael Martin
Sign In or Register to comment.