no code implementations • 19 Jun 2020 • Yeojoon Youn, Neil Thistlethwaite, Sang Keun Choe, Jacob Abernethy
We propose a novel approach that resolves many of these issues by relying on a kernel-based non-parametric discriminator that is highly amenable to online training---we call this the Online Kernel-based Generative Adversarial Networks (OKGAN).