A Primer on Resilient Intelligent Systems

Challenge #1 — Adversaries

Challenge #2 — Offline/Online Mismatch

Challenge #3 — Feedback Loops

  • Most recommender systems don’t receive user feedback on any sample that the system did not previously recommend.
  • Systems that effectively detect and penalize users for certain behaviors may cause users to modify their behavior to avoid penalty.
  • If a content moderation system is trained on user reports, then increases in system coverage may elicit decreases in model training data as user report rates decrease.

Challenge #4 — Outages

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
ODSC - Open Data Science

ODSC - Open Data Science

93K Followers

Our passion is bringing thousands of the best and brightest data scientists together under one roof for an incredible learning and networking experience.