AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Sara Hooker: Cohere For AI, the Hardware Lottery, and DL Tradeoffs
The Gradient: Perspectives on AI
Is There a Trait Off Between Sparsity and Performance?
How we've measured trade off has really been in terms of a top level performance ic, an metric of some kind. And so when we measure trade offs ot compression, we should also take into account these other other objectives. What i will say is that it's not that this is always a loss. Some of my recent work with colleagues has shown that if you take into account desperate erorate or worse class error, you can actually design objectives which improve oval performance.
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