Snipd home pageGet the app
public
Data Skeptic chevron_right

GANs Can Be Interpretable

Jul 11, 2020
26:39
forum Ask episode
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
1
Introduction
00:00 • 2min
chevron_right
2
How Do You Create Amazing Effects With Your Research?
02:21 • 3min
chevron_right
3
How to Control a Generative Anomaly on Network
05:40 • 2min
chevron_right
4
Is There a Way to Order the Principal Components?
07:52 • 5min
chevron_right
5
Spring Board Data Science Career Track
12:40 • 2min
chevron_right
6
Can Pc a Be Run at Any of the Intermediate Layers of the Generator?
15:04 • 3min
chevron_right
7
A Colab Note Book - Part 1
18:00 • 2min
chevron_right
8
Is There a Future in Modeling?
19:36 • 3min
chevron_right
9
Is There a Parallel Line of Research in Machine Learning?
22:25 • 2min
chevron_right
10
The Evolution of the Tool Kit for Ml Practitioners
24:07 • 2min
chevron_right

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.

HomeTop podcastsPopular guests