Research talk: Computationally efficient large-scale AI
195
Microsoft Research336 тыс
Следующее
08.02.22 – 722:28Популярные
128 дней – 1 9576:09
344 дня – 2 6053:17Опубликовано 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
1 день – 30 45541:42
3 дня – 7 128 1321:39
Случайные видео
357 дней – 123 92710:10
09.09.23 – 5 9641:29:01
16.04.23 – 4 8042:12
31.10.21 – 2 508 12728:34
23.08.21 – 3 4121:13:18
26.02.20 – 4 902 16118:29
2 дня – 6630:57
7 дней – 1 352 4300:31
17 дней – 8 6141:17
19 дней – 93 61414:36
20 дней – 605 6512:58:34