Reinforced Self-Training (ReST) for Language Modeling (Paper Explained)
Why it's on BrighterTube
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceAnalyzes reinforced self-training for language model improvement. Technical explanation of learning method combining data synthesis and training.
What you'll learn
A 53-minute video from Yannic Kilcher: “Reinforced Self-Training (ReST) for Language Modeling (Paper Explained)”.
Video by Yannic Kilcher, played through YouTube's embedded player.
Part of Generative Models, Reinforcement Learning, Papers Explained