Post
Balaji Srinivasan @balajis · Jul 3, 2021
  • From Twitter

Good thread on the last mile problem for deep learning. The main thing that’s worked in the successful production ML apps I’ve supervised (from variant calling to anti-fraud) is a cheap, fast feedback loop to turn new in-field training examples into online model updates.

Recommended by 1 person
1 mention
Share on Twitter Repost
Replies
Reply
No replies yet