Channel Gating for Cheaper and More Accurate Neural Nets with Babak Ehteshami Bejnordi - #385

episode

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

Related

recent transcribed audio

Bringing Kashmir’s lakes back to life 25 min · 23 Sep 2026 · The Documentary Podcast

Soup 56 min · 23 Sep 2026 · Three Bean Salad

AFL Record Editor Ash Browne | Grand Final edition on sale now! (23.09.26) 2 min · 23 Sep 2026 · Whateley

NPR News: 09-22-2026 8PM EDT 4 min · 23 Sep 2026 · NPR News Now

Send Me To Sleep | Aristotle 44 min · 23 Sep 2026 · Send Me To Sleep

Finding the balance between offence & defence | The Art of Coaching with Ken Hinkley! (23.09.26) 5 min · 23 Sep 2026 · Whateley

Report any issue

Source

Recorded22 Jun 2020

Publisherfeeds.megaphone.fm ↗

Handlerec:12496152

Show notes

Today we’re joined by Babak Ehteshami Bejnordi, a Research Scientist at Qualcomm. Babak is currently focused on conditional computation, which is the main driver for today’s conversation. We dig into a few papers in great detail including one from this year’s CVPR conference, Conditional Channel Gated Networks for Task-Aware Continual Learning, covering how gates are used to drive efficiency and accuracy, while decreasing model size, how this research manifests into actual products, and more!

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in