When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

299 views

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Technical talk on when memorization of irrelevant data is necessary for learning. Explains theoretical limits of generalization in machine learning.

A 10-minute video from Google TechTalks: “When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?”.

Video by Google TechTalks, played through YouTube's embedded player.

Part of 2021 Google Workshop on Federated Learning and Analytics