A new architecture for computer vision based on a sparse mixture of experts unlocks the training of large models by routing different inputs to different paths, and achieves top accuracy with about half the compute. Learn more and grab the code → https://t.co/0ciUcukgtp https://t.co/R6eIab8wXS

Favorite tweet:
A new architecture for computer vision based on a sparse mixture of experts unlocks the training of large models by routing different inputs to different paths, and achieves top accuracy with about half the compute. Learn more and grab the code → https://t.co/0ciUcukgtp https://t.co/R6eIab8wXS https://twitter.com/GoogleAI/status/1481693883465711617 https://t.co/0ciUcukgtp January 14, 2022 at 03:25AMA new architecture for computer vision based on a sparse mixture of experts unlocks the training of large models by routing different inputs to different paths, and achieves top accuracy with about half the compute. Learn more and grab the code → https://t.co/0ciUcukgtp https://t.co/R6eIab8wXS
— Google AI (@GoogleAI) Jan 13, 2022
댓글
댓글 쓰기