Learning Long-Time Dependencies with RNNs w/ Konstantin Rusch - #484

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

5 On It & reacting to Bears locker room sound (Hour 3) 41 min · 21 Sep 2026 · Rahimi & Grote Show

Anthony Herron shares observations from Bears' ugly loss to Vikings (Hour 2) 41 min · 21 Sep 2026 · Rahimi & Grote Show

Caleb Williams exits with hamstring injury in Bears' 9-3 loss to Vikings (Hour 1) 37 min · 21 Sep 2026 · Rahimi & Grote Show

Bears reflect on their struggles in 9-3 loss to Vikings 11 min · 21 Sep 2026 · Rahimi & Grote Show

5 On It: Reacting to optimistic injury news on Caleb Williams 20 min · 21 Sep 2026 · Rahimi & Grote Show

Report any issue

Source

Recorded17 May 2021

Publisherfeeds.megaphone.fm ↗

Handlerec:12496052

Show notes

Today we conclude our 2021 ICLR coverage joined by Konstantin Rusch, a PhD Student at ETH Zurich. In our conversation with Konstantin, we explore his recent papers, titled coRNN and uniCORNN respectively, which focus on a novel architecture of recurrent neural networks for learning long-time dependencies. We explore the inspiration he drew from neuroscience when tackling this problem, how the performance results compared to networks like LSTMs and others that have been proven to work on this problem and Konstantin’s future research goals. The complete show notes for this episode can be found at twimlai.com/go/484.

Ask this episode

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

Sign in