Arxiv Papers

The boundary of neural network trainability is fractal


Listen Later

Fractals in neural networks: exploring boundaries between stable and divergent training. Similarities in iteration processes, hyperparameter sensitivity. Fractal boundary found over vast scales in all configurations.


https://arxiv.org/abs//2402.06184


YouTube: https://www.youtube.com/@ArxivPapers


TikTok: https://www.tiktok.com/@arxiv_papers


Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016


Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers


...more
View all episodesView all episodes
Download on the App Store

Arxiv PapersBy Igor Melnyk

  • 5
  • 5
  • 5
  • 5
  • 5

5

3 ratings


More shows like Arxiv Papers

View all
Exchanges by Goldman Sachs

Exchanges

978 Listeners

Odd Lots by Bloomberg

Odd Lots

1,986 Listeners

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) by Sam Charrington

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

434 Listeners

The Daily by The New York Times

The Daily

113,026 Listeners

All-In with Chamath, Jason, Sacks & Friedberg by All-In Podcast, LLC

All-In with Chamath, Jason, Sacks & Friedberg

10,203 Listeners

Hard Fork by The New York Times

Hard Fork

5,574 Listeners

UnHerd with Freddie Sayers by UnHerd

UnHerd with Freddie Sayers

219 Listeners

Unsupervised Learning with Jacob Effron by by Redpoint Ventures

Unsupervised Learning with Jacob Effron

53 Listeners

Latent Space: The AI Engineer Podcast by Latent.Space

Latent Space: The AI Engineer Podcast

100 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

459 Listeners