The Case for Hardware-ML Model Co-design with Diana Marculescu - #391

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

NPR News: 09-22-2026 7PM EDT 4 min · 22 Sep 2026 · NPR News Now

US-Iran Talks on Sidelines of UN Summit, Chipmakers Rally, More 7 min · 22 Sep 2026 · Bloomberg News Now

7PM ET 09/22/2026 Newscast 3 min · 22 Sep 2026 · Fox News Hourly Update

Dentists Are Making Millions From This Lie - Dr. Ellie Phillips EXPOSES the dental industry 1h 5m · 22 Sep 2026 · Redacted News

Inside Big Brother: Nasty Nick (Ep 1) 39 min · 22 Sep 2026 · The Rest Is Entertainment

Jon Ronson on Conspiracy, Masculinity and Writing 1h 46m · 22 Sep 2026 · The Blindboy Podcast

Report any issue

Source

Recorded13 Jul 2020

Publisherfeeds.megaphone.fm ↗

Handlerec:12496146

Show notes

Today we’re joined by Diana Marculescu, Professor of Electrical and Computer Engineering at UT Austin. We caught up with Diana to discuss her work on hardware-aware machine learning. In particular, we explore her keynote, “Putting the “Machine” Back in Machine Learning: The Case for Hardware-ML Model Co-design” from CVPR 2020. We explore how her research group is focusing on making models more efficient so that they run better on current hardware systems, and how they plan on achieving true co

Ask this episode

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

Sign in