Re:Pac-Man recreated with a GAN trained on 50k game episodes
by kevincox on Friday May 22, 2020 @07:42PM
(#23278384)
Exactly. It is sort of like saying the first transistor was too expensive to be practical.
Development always starts with some novel technology that has major flaws, but some good nuggets. Then it is further developed to be practical.
Re:Pac-Man recreated with a GAN trained on 50k game episodes
by ekelsen on Saturday May 23, 2020 @11:35AM
(#23283765)
One minor nit: The recent FB blogpost wasn't really "research" - it was mostly a reimplementation of this paper: https://arxiv.org/abs/1802.08435
I don't see that trend. Bleeding edge research has always been beyond what's practical, by its very nature. The focus is on pushing the boundaries, not to build something efficient/commercial.
It's the followup work that makes it practical. See for example the evolution of WaveNet. It was breakthrough research, but yeah it wasn't practical. Now a couple years later and we're generating speech on mobile devices of similar quality (see the recent Facebook research), and able to teach these machines using orders of magnitude less data (see 15.ai).
Not to mention the plethora of research that is explicitly about making neural networks more efficient and easier to train (e.g. EfficientNet; 1cycle; etc).
Bleeding edge stuff like AlphaStar, BigGAN, GPT-2, etc are just that: bleeding edge. They'll get more efficient and practical every year, just like everything else in machine learning.