Real-OPT. A way to fine-tune AI models more efficiently by reparameterizing how they learn.

github.com/topjohnwu/Real-OPT-Parameterization

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

June 2017
  • Adapt to cec2005 problems
  • Generalize to high dimension
May 2017
  • 1-dimen check done
  • Add half done code
  • Initial commit