First 1e6 integers, represented as binary vectors indicating their prime factors, and laid out using the sparse matrix support in @leland_mcinnes's UMAP dimensionality reduction algorithm. This is from a 1000000x78628 (!) binary matrix. Very pretty structure emerges.
Excited about expanding the Google Brain team in Tokyo. If you are excited to work on fresh and interesting AI research, please consider applying! https://t.co/SCI9AyppSN
As a researcher it is humbling when someone reads your work, and cares enough to reimplement the core ideas from the ground up to reproduce and extend parts of the experiments, and also share the results in a nice blog post. I wrote some comments about it: https://t.co/0KTZ25nSDL