AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Parallelism and Acceleration for Large Language Models with Bryan Catanzaro - #507
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is There Any Elements of Attention in Machine Learning?
The motion factors tell us how objects are moving. And you can imagine how useful that is for reconstruction, because part of the benefit of a temporal reconstruction method is that you can use samples from prior frames. But just because something is moving geometrically doesn't mean that its appearance is moving geometrially. So this is kind of an interesting problem for machine learning to figure out,. It's very difficult to write down the rules as a human for how to do this temporal gration problem, sort of human heristic. May get better and better but it's actually quite a challenging problem.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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