It feels like there would be some win in going full deep learning on the voip dropped packet mitigation problem — train up on terabytes of conversation, then be able to predict the next 100 ms or so of a voice stream if packets don’t arrive.
Replying to @ID_AA_Carmack @jangray
There are so many ways this could go wrong, ranging up to active exploits.
9:06 AM - 5 May 2018
0 replies
0 retweets
2 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.