AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Daniel Situnayake: AI on the Edge
The Gradient: Perspectives on AI
The Future of Machine Learning
The work that's been done around model compression. quantization is just this idea that typically you're training a model, the weights and other parameters are expressed as 32 bits floating point values. But it turns out that because deep learning is awesome, you can actually reduce the precision of these numbers,. And often not really see much deterioration in the performance of your model. So obviously the size is getting shrunken down by a factor of four.
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