I'm looking to narrow down the subject for my bachelor thesis: I am currently working on a project, that only offers a small dataset and there will be no more data incoming for now. What I'm trying to do now, is optimizing my neural net with augmented data, produced by a GAN.

Mostly, I just find GANs that are being used for images. What I am trying to predict are machines that can be used for production. Does anybody here know about possiblities, sources or other ideas that fit to this topic? Any help would be welcome!

The only source I found, yet is this one: https://arxiv.org/pdf/1809.00981.pdf

  • $\begingroup$ "What I am trying to predict are machines that can be used for production." What exactly are you trying to predict? $\endgroup$ – S. Kolassa - Reinstate Monica Jul 6 at 14:11
  • $\begingroup$ The attributes of the resources. So I am predicting the different attributes (some are flags, some are values) resulting in a fictive resource and afterwards I run a filter over them, in order to find the resource, that matches the prediction the most $\endgroup$ – nicenoize Jul 6 at 14:58
  • $\begingroup$ So, some of your attributes are discrete (binary) and some continuous (?). And I guess you want to predict the machines to be used for production. This seems a classification task from the description, not a generation. $\endgroup$ – GrigorisG Jul 26 at 16:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.