
Machine Learning Embeddings with Edo Liberty
Programming Throwdown
00:00
The Quantitization of the Dot Product
So, so the quantitization, you're saying that through that, you don't necessarily need a tree. Ye yea. I think that that itit makes a toni sent. Ke, what about ball tree or v p trees, or these other things? Is he quantitification, just the fact that you can parallelyze it, maybe on a g p or something, does that make that more appealing than these other sort of tree ideas? Yes. So thee, there there are two factors the plane. One of them is the hardwell,. like some some arguitms just just lend themselves really well to the kind of hadwe that you have.
Transcript
Play full episode