Learning to Ponder: Memory in Deep Neural Networks with Andrea Banino - #528

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

Transrapid, Flugtaxis, Hyperloop – Warum es neuartige Verkehrstechnik so schwer hat 28 min · 22 Sep 2026 · Das Wissen | SWR

Dan Wiederer talks Tyson Bagent's opportunity to shine (Hour 4) 41 min · 21 Sep 2026 · Rahimi & Grote Show

Trump Bans CNN, MS NOW & Politico: What the Law Says | Greenland Deal + AI Force 35 min · 21 Sep 2026 · UNBIASED Politics

Trump takes the world stage 18 min · 21 Sep 2026 · The NPR Politics Podcast

4PM ET 09/21/2026 Newscast 3 min · 21 Sep 2026 · Fox News Hourly Update

H1 Monologue, Chiefs Overtime Win! 41 min · 21 Sep 2026 · The Program

Report any issue

Source

Recorded18 Oct 2021

Publisherfeeds.megaphone.fm ↗

Handlerec:12496008

Show notes

Today we’re joined by Andrea Banino, a research scientist at DeepMind. In our conversation with Andrea, we explore his interest in artificial general intelligence by way of episodic memory, the relationship between memory and intelligence, the challenges of applying memory in the context of neural networks, and how to overcome problems of generalization. We also discuss his work on the PonderNet, a neural network that “budgets” its computational investment in solving a problem, according to the inherent complexity of the problem, the impetus and goals of this research, and how PonderNet connects to his memory research. The complete show notes for this episode can be found at twimlai.com/go/528.

Ask this episode

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

Sign in