Training more effective learned optimizers, and using them to train themselves (Paper Explained)

About this video

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

Covers learned optimizers trained to optimize other networks, including recursive application. Teaches meta-learning approach to algorithm design.

A 54-minute video from Yannic Kilcher: “Training more effective learned optimizers, and using them to train themselves (Paper Explained)”.

Video by Yannic Kilcher, played through YouTube's embedded player.

Part of General Machine Learning, Papers Explained