Why AI Researchers Are Suddenly Obsessed With Whirlpools (Ep. 297) [RB]

About this episode

This episode discusses how VortexNet utilizes whirlpools to enhance neural networks and tackle deep learning challenges.

VortexNet uses actual whirlpools to build neural networks. Seriously. By borrowing equations from fluid dynamics, this new architecture might solve deep learning's toughest problems—from vanishing gradients to long-range dependencies. Today we explain how vortex shedding, the Strouhal number, and turbulent flows might change everything in AI. Sponsors This episode is brought to you by Statistical Horizons At Statistical Horizons, you can stay ahead with expert-led livestream seminars that make data analytics and AI methods practical and accessible.Join thousands of researchers and professionals who’ve advanced their careers with Statistical Horizons.Get $200 off any seminar with code DATA25 at https://statisticalhorizons.com References https://samim.io/p/2025-01-18-vortextnet/

People in this episode

Host: Francesco Gadaleta

Topics covered

• AI
• neural networks
• fluid dynamics
• deep learning
• whirlpools
• vortex shedding

Keywords

• VortexNet
• whirlpools
• neural networks
• fluid dynamics
• deep learning
• vanishing gradients
• Strouhal number
• turbulent flows

Sponsors

Statistical Horizons

Mentioned in this episode

Books & works: VortexNet

More episodes of Data Science at Home

• The propaganda algorithm (Ep. 308) · May 30, 2026 · 16 min
• AI tips & tricks (Ep. 307) · May 19, 2026 · 55 min
• AI and videogames: Conversational NPCs (Ep. 306) · May 7, 2026 · 52 min
• AI and videogames (Ep. 305) · May 5, 2026 · 50 min
• Europe, wake up! You Can't Be a Superpower on Someone Else's Servers (Ep. 304) · April 21, 2026 · 28 min
• Social media is an ant mill (Internet is a disaster) (Ep. 303) · April 7, 2026 · 35 min