Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceExplains Switch Transformers' sparse routing mechanism for scaling to trillion parameters efficiently. Paper walkthrough of a major scaling technique for large models.
A 34-minute video from Yannic Kilcher: “Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity”.
Video by Yannic Kilcher, played through YouTube's embedded player.
Part of Natural Language Processing, Deep Learning Architectures, Papers Explained