Evaluating Model Explainability Methods with Sara Hooker - TWiML Talk #189

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

Full Show Podcast: 23 September 2026 1h 29m · 22 Sep 2026 · The Mike Hosking Breakfast

Evening Wire: Trump Delivers Remarks to the UN & Nolan Wells Drowning Updates | 9.22.26 11 min · 22 Sep 2026 · Morning Wire

Willie Robertson Wouldn’t Let His Kids Open Their Own Gifts | Duck Call Room #589 59 min · 22 Sep 2026 · Duck Call Room

🎙Tell us your Group Chat Names - The Chat 10 min · 22 Sep 2026 · The Hauraki Breakfast Podcast

MORNING TEA: Taylor Swift's Surprise New Single & William and Kate Hit The Red Carpet With Tom Cruise 7 min · 22 Sep 2026 · The Spill

Trump Touts Foreign Policy Vision in UN Speech Ahead of Midterms 13 min · 22 Sep 2026 · WSJ What’s News

Report any issue

Source

Recorded10 Oct 2018

Publisherfeeds.megaphone.fm ↗

Handlerec:12496349

Show notes

In this, the first episode of the Deep Learning Indaba series, we’re joined by Sara Hooker, AI Resident at Google Brain. I spoke with Sara in the run-up to the Indaba about her work on interpretability in deep neural networks. We discuss what interpretability means and nuances like the distinction between interpreting model decisions vs model function. We also talk about the relationship between Google Brain and the rest of the Google AI landscape and the significance of the Google AI Lab in Accra, Ghana.

Ask this episode

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

Sign in