31: Ian Goodfellow on Inventing GANs

https://is1-ssl.mzstatic.com/image/thumb/Podcasts126/v4/a5/dc/c6/a5dcc602-4684-a028-da06-0dbef86881f7/mza_5248422593643283519.jpg/600x600bb.jpg

Le Random

32 episodes

6 days ago

Le Random is building a digital generative art institution that contextualizes and elevates generative art. We achieve this in two ways. First, we are assembling a historically encompassing, chain-agnostic generative art collection. Second, we publish content that enables the generative art community to understand its past, curate its present and celebrate its future. This includes an Editorials section, our book-length Generative Art Timeline and our multimedia content here and on YouTube. This is the home of Le Random's audio content.

Visual Arts

Arts

RSS

All content for Le Random is the property of Le Random and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Visual Arts

Arts

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/39939699/39939699-1705404286628-c1cd38575b4c8.jpg

31: Ian Goodfellow on Inventing GANs

Le Random

1 hour 24 minutes 55 seconds

1 week ago

31: Ian Goodfellow on Inventing GANs

In this extra special episode, host Peter Bauman (Le Random's editor in chief) speaks with prominent AI researcher Ian Goodfellow about the legendary origins of GANs, their unexpected success and indelible impact on both twenty-first-century image making and AI research.

This episode contains Peter and Ian's full conversation and serves as a companion to Monday's written interview, which covered the first half of the discussion only.

Monday's editorial: https://www.lerandom.art/editorial/ian-goodfellow-on-inventing-gans

Chapters 📖:

[00:00:03]: Introduction and cultural impact of GANs

[00:03:30]: Ian explains GANs and game theory

[00:06:12]: The Montreal origin story begins

[00:10:51]: The first GAN and MNIST success

[00:19:36]: Early reception and longevity surprises

[00:21:22]: LAPGAN and DCGAN mark takeoff

[00:23:54]: Is generative modeling deep learning’s culmination?

[00:26:11]: Can GANs be creative or just mimic?

[00:29:30]: GANs as tools; human creativity’s role

[00:37:14]: On autonomous AI artists and personhood

[00:41:50]: GANs’ role in text-to-image’s emergence

[00:42:20]: Story from probabilistic graphs to media generation

[00:51:30]: Key GAN advances: LAPGAN to StyleGAN and beyond

[00:57:52]: Are engineers artists?

[01:02:26]: Expected uses, misuse risks, and simulations

[01:06:50]: Scale’s legacy, spending, and scaling laws

[01:11:31]: AGI timelines and being wrong both ways

[01:19:14]: Platonic representations across modalities

[01:23:49]: Closing thanks and farewells