Here's my presentation where I explored #tensorflow to make a neural network spatial curve based on an autoencoder.
https://www.youtube.com/watch?v=S_8_trOCVjI
You can follow along with my code diffs. https://github.com/RangerMauve/neural-spatial-curves/commits/default/
Friendly reminder that you should consider everything you say on the Fediverse to be publicly available and archived by your adversaries, who can and will use it against you.
"Quiet public" isn't saving you from that. "Followers-only" isn't saving you from that. Don't assume your DMs are private either.
Occult Enby that's making local-first software with peer to peer protocols, mesh networks, and the web.
Exploring what a local-first cyberspace might look like in my spare time.