Michael Gillhofer, Hubert Ramsauer, Johannes Brandstetter, and Sepp Hochreiter

We propose a GAN based approach to solve inverse problems which have non-differentiable or even black-box forward relations.  The idea is to find solutions via an adversarial game where the generator has to propose new samples and the discriminator has to assess the quality of the samples with respect to the forward relation  f .  However, instead of attempting to approximate  f  directly, the discriminator only has to solve a binary classification task in local regions populated by the generated samples.  We demonstrate the efficacy of our approach by applying it to an artificially generated topology optimization problem.  We show that our method leads to results similar to those of more traditional topology optimization methods.

33rd Conference on Neural Information Processing Systems (NeurIPS 2019); e-print at openreview.net

Download
View paper
IARAI Authors
Dr Sepp Hochreiter
Research
Generative Adversarial Networks
Keywords
Generative Adversarial Networks

©2023 IARAI - INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE

Imprint | Privacy Policy

Stay in the know with developments at IARAI

We can let you know if there’s any

updates from the Institute.
You can later also tailor your news feed to specific research areas or keywords (Privacy)
Loading

Log in with your credentials

Forgot your details?

Create Account