Josh Wolfe @wolfejosh VC, entrepreneur, fund manager @Lux_Capital; Chair @CiPrep Coney Island Prep; Trustee @SfiScience Santa Fe Inst; CoFounder of Carson, Quinn & Bodhi w/ @ltwolfe Mar. 02, 2018 1 min read

1/ A few REMARKABLE things here

First (via sci-fi author @robinsloan) exploration of idea of "variational autoencoding....

2/How can you go from RANDOM Sentence 1 (INPUT) to random unrelated Sentence 2 (INPUT)...and get OUTPUT of new sentences with meaning between them to connect them 

3/ He poses:

4/ There may be a linear gradient between the 2 this:

5/ But it's way more likely to be multi-dimensional manyfold beyond even THIS:

6/ Like smooth morphing visually going from face of PERSON 1 to face of PERSON 2. Like THIS:

7/ But also notable is WHERE the researchers doing + inspiring the work are based...
First paper

8/ Next paper...(China)...

9/ And Next a year later...Germany...

10/ WHY interesting to me? If you can generate from INPUT 1 to INPUT 2 a set of PATHS from possibility space (from sentences, photos). You can do GENERATIVE DESIGN to solve design + art 'problems'

But you can also soon generate hypotheses from CAUSE to EFFECT to..


You can follow @wolfejosh.


Tip: mention @threader_app on a Twitter thread with the keyword “compile” to get a link to it.

Enjoy Threader? Sign up.

Threader is an independent project created by only two developers. The site gets 500,000+ visits a month and our iOS Twitter client was featured as an App of the Day by Apple. Running this space is expensive and time consuming. If you find Threader useful, please consider supporting us to make it a sustainable project.