Training a neural network using differential evolution (genetic algorithm)

tassawar_ali
tassawar_ali New Altair Community Member
edited November 2024 in Community Q&A
Hello

i am beginner in Rapidminer. I've recently installed Rapidminer 9.0. Please guide me about implementing " Training a neural network using DE". Ist thing is: can we implement it in Rapidminer?? or i've to go to python for doing so.

Experts please guide. 

Answers

  • hughesfleming68
    hughesfleming68 New Altair Community Member
    edited April 2019
    I am assuming that you are trying to reproduce a research paper? If that is the case then it would be helpful to have a link or the paper itself. Rapidminer has evolutionary (genetic) parameter and feature selection if that is what you are looking for. Nothing beats experimenting.
  • SGolbert
    SGolbert New Altair Community Member
    Hi,

    I think that you refer to using an evolutionary algorithm instead of forward-backward propagation for the training of  neural net. While you can do it in RapidMiner if you want, you would have to do it at the Java level. It's probably easier to do it in R or Python.

    Regards,
    Sebastian