training algorithm issue

Bipraneel
2013-02-24
2013-02-24
  • Bipraneel

    Bipraneel - 2013-02-24

    Hi,

    I am a student and doing my dissertation (DoS attacks in Wi-Fi) work. Could anyone please suggest as how to use different training algorithms other than Back-propagation (like Scaled conjugate gradient / Quasi-Newton ) in Neuroph?

    For my project I need to train the network with different training algorithms (other than those which are already provided in Neuroph). Is it possible to train the network with Scaled-Conjugate-Gradient Algo in Neuroph? If yes, then how?

    Please suggest.

    Thank you.

     
  • Zoran Sevarac

    Zoran Sevarac - 2013-02-24

    Yes it possible, but its still not implemented. However it shoul dnot be hard to do, my guess is you'll have to extend and modify original Backpropagation class. That would be great contribution to Neuroph. Let me know if you decide to implement it I'll provide more help.

    Zoran

     

Log in to post a comment.

Get latest updates about Open Source Projects, Conferences and News.

Sign up for the SourceForge newsletter:

JavaScript is required for this form.





No, thanks