2min chapter

The Thesis Review cover image

[13] Adji Bousso Dieng - Deep Probabilistic Graphical Modeling

The Thesis Review

CHAPTER

The Importance of Topic Transformers in Deep Learning

I would be interested if someone, yeah, does a topic transformer because transformers have actually been shown to also have a long-term long-term dependency problem. So I would be interested to see what you get when you apply the same generative process, but using a transformer as a neural net parameterization. Yeah. It can be any nonlinear function. The name is unfortunate because it makes it seem like it's just for RNNs, LSTMs and the light. But if you look at the part where you're capturing, where youwhere you're trying to capture locality, that's a non linear function.Yeah. That's nice. This notion of like global versus

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