Pathologies of Neural Models and Interpretability with Alvin Grissom II - TWiML Talk #229

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

The Songs of John Farnham: A Living Legend | Tony Cochrane (23.09.26) 7 min · 23 Sep 2026 · Whateley

Las 10 de Erazno, el Chokolatazo, Parodias, 1h 29m · 23 Sep 2026 · Erazno y La Chokolata El Podcast

Steve Hilton & Spencer Pratt: Fixing California, Cheaper Gas, Ballot Fraud & CA Republicans 55 min · 23 Sep 2026 · All-In with Chamath, Jason, Sacks & Friedberg

Optics of Alastair Clarkson's brunt sacking | The Eminently Sensible Phil Davis (23.09.26) 1 min · 23 Sep 2026 · Whateley

The Eminently Sensible Phil Davis | Whateley (23.09.26) 13 min · 23 Sep 2026 · Whateley

The impact of Zak Butters' homecoming | The Eminently Sensible Phil Davis (23.09.26) 1 min · 23 Sep 2026 · Whateley

Report any issue

Source

Recorded11 Feb 2019

Publisherfeeds.megaphone.fm ↗

Handlerec:12496309

Show notes

Today, we continue our Black in AI series with Alvin Grissom II, Assistant Professor of Computer Science at Ursinus College. In our conversation, we dive into the paper he presented at the workshop, “Pathologies of Neural Models Make Interpretations Difficult.” We talk through some of the “pathological behaviors” he identified in the paper, how we can better understand the overconfidence of trained deep learning models in certain settings, and how we can improve model training with entropy regulariz

Ask this episode

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

Sign in