GANs Can Be Interpretable
Data Skeptic
English - July 11, 2020 02:42 - 26 minutes - 30.5 MB - ★★★★★ - 477 ratingsScience Technology machinelearning datamining datascience science skepticism statistics Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Previous Episode: Sentiment Preserving Fake Reviews
Next Episode: Authorship Attribution of Lennon McCartney Songs
Erik Härkönen joins us to discuss the paper GANSpace: Discovering Interpretable GAN Controls. During the interview, Kyle makes reference to this amazing interpretable GAN controls video and it’s accompanying codebase found here. Erik mentions the GANspace collab notebook which is a rapid way to try these ideas out for yourself.