News for hackers. Stuff that matters.

A comment on Show HN: 3d Word Vectors with Neural Networks, T-SNE, and WebGL. Parent comment

Re:Show HN: 3d Word Vectors with Neural Networks, T-SNE, and... by a1k0n on Thursday November 14, 2013 @10:09AM (#6732696)
Have you tried messing with the target perplexity? That seems to make a big difference.
[ Parent | on HN ]
Re:Show HN: 3d Word Vectors with Neural Networks, T-SNE, and... by dave_sullivan on Thursday November 14, 2013 @10:42AM (#6732891)
Yeah, I've tried from .5 to 50--3 seems to be the best value currently. I may try it with the non Barnes-Hut implementation too, maybe on a smaller number of words. If that works, then I'll bet it is something related to how the quadtree is constructed...

Btw, nice LDA visualization!

[ Parent | on HN ]