AI for High-Stakes Decision Making with Hima Lakkaraju - #387

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 12PM EDT 5 min · 22 Sep 2026 · NPR News Now

12PM ET 09/22/2026 Newscast 3 min · 22 Sep 2026 · Fox News Hourly Update

Des Décisions Difficiles À Venir Pour Le Canadien | Le Sick Podcast Avec Tony Marinaro 22/09/26 1h 31m · 22 Sep 2026 · The Sick Podcast with Tony Marinaro / Le Sick Podcast avec Tony Marinaro

JTP: Bateman Hurt, 2027 Lookahead & Bisons’ Josh Winckowski 1h 39m · 22 Sep 2026 · Blue Jays Talk

ep 399 | What does a Fed hiking cycle mean for markets? 8 min · 22 Sep 2026 · On Point

Ep. 2065 - How They Legally Killed An 83-Year-Old Grandmother 46 min · 22 Sep 2026 · The Michael Knowles Show

Report any issue

Source

Recorded29 Jun 2020

Publisherfeeds.megaphone.fm ↗

Handlerec:12496150

Show notes

Today we’re joined by Hima Lakkaraju, an Assistant Professor at Harvard University. At CVPR, Hima was a keynote speaker at the Fair, Data-Efficient and Trusted Computer Vision Workshop, where she spoke on Understanding the Perils of Black Box Explanations. Hima talks us through her presentation, which focuses on the unreliability of explainability techniques that center perturbations, such as LIME or SHAP, as well as how attacks on these models can be carried out, and what they look like.

Ask this episode

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

Sign in