Research talk: Computationally efficient large-scale AI
176
Microsoft Research321 тыс
Следующее
08.02.22 – 642:28Популярные
14 дней – 44757:52
96 дней – 6215:18Опубликовано 8 февраля 2022, 15:57
Speaker: Song Han, Assistant Professor, MIT
Today’s AI is too big. Deep neural networks demand extraordinary levels of computation, and therefore power and carbon, for training and inference. In this research talk, Song Han, MIT, presents TinyML and efficient deep learning techniques that make AI greener, smaller, faster, and deployable on IoT devices.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Today’s AI is too big. Deep neural networks demand extraordinary levels of computation, and therefore power and carbon, for training and inference. In this research talk, Song Han, MIT, presents TinyML and efficient deep learning techniques that make AI greener, smaller, faster, and deployable on IoT devices.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Свежие видео
3 часа – 34519:50
4 дня – 1 2090:39
4 дня – 3911:00
4 дня – 1601:43
5 дней – 24 8268:08Случайные видео
218 дней – 24 8181:14
05.08.22 – 43 9725:59
16.06.22 – 16 2200:32
30.05.22 – 52 4819:15
10.09.13 – 524 1639:58
2 дня – 418 6853:38:35
3 дня – 24157:05
5 дней – 1 7692:28
5 дней – 6268:49
7 дней – 6 8160:30
7 дней – 10 7712:18
10 дней – 21 7281:58