2min chapter

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

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

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

Using a Short Transformer in a Language Model?

Some short transformer thise models have shown some of the properties of this kind of memory. But it's very difficult to scale up those models because they require a lot of computation. We don't know yet how to make that model bek to a scale where they actual full to target very complex problem. There are now papers trying to deal with that and reduce the complexity to leneal size.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode