

Computer programmer and scientist. Currently Programmer-at-Large for freelance specialty work.
The University of Michigan recently banned employees from sitting on yoga balls due to “catastrophic failures.” Since yoga balls are made out of cheap plastic, it’s not a question of if the ball will pop, but when. People go straight to the ground.
This paper differs from earlier work: the training algorithm is backed up by theory, and few examples exist where theory-justified papers gave good empirical results. The big thing about WGANs is that developers can train their discriminator to convergence, which was not possible earlier. Doing this eliminates the need to balance generator updates with discriminator updates.