This is utterly wild... am I a little smooth-brained, or is this totally unrealistic?
- 200 Mbps compressed to under 1 Mbps
- Realtime, i.e: ~1ms latency or better
- Encode and transmit in <10mW (yes, including radio)
- Lossless
- High-entropy input
... if you succeed, just email them your solution - no mention of any reward or Nobel Prize nomination.
https://content.neuralink.com/compression-challenge/README.html
@attie The 200Mbps -> 1Mbps isn't ridiculous *if* the data isn't high entropy. Almost certainly okay for the result to be lossy, and almost certainly required for it to be specific to neuralink data, not generic data. Which means lossy is very likely okay-or-better, especially with their other constraints.
This looks like recruiting, so it won't be a production-grade solution. You'll email them an idea outline or a proof of concept to show you can do something like that, then they'll hire you.
They explicitly ask for lossless though. (To be fair, asking for lossy requires having a loss metric, which requires a good understanding of what's signal and what's noise.)
@robryk @attie Ah, good call. Sorry, you're right, they *do* ask for lossless.