Going meta: learning algorithms and the self-supervised machine with Dr. Philip Bachman [Podcast]
1 506
12.6
Microsoft Research333 тыс
Следующее
06.12.19 – 25 94444:35Популярные
63 дня – 4319:39
190 дней – 6223:07:51Опубликовано 4 декабря 2019, 11:15
Episode 101 | December 4, 2019
Deep learning methodologies like supervised learning have been very successful in training machines to make predictions about the world. But because they’re so dependent upon large amounts of human-annotated data, they’ve been difficult to scale. Dr. Phil Bachman, a researcher at MSR Montreal, would like to change that, and he’s working to train machines to collect, sort and label their own data, so people don’t have to.
Today, Dr. Bachman gives us an overview of the machine learning landscape and tells us why it’s been so difficult to sort through noise and get to useful information. He also talks about his ongoing work on Deep InfoMax, a novel approach to self-supervised learning, and reveals what a conversation about ML classification problems has to do with Harrison Ford’s face.
See more on this and other Microsoft Research podcast episodes: microsoft.com/en-us/research/b...
Deep learning methodologies like supervised learning have been very successful in training machines to make predictions about the world. But because they’re so dependent upon large amounts of human-annotated data, they’ve been difficult to scale. Dr. Phil Bachman, a researcher at MSR Montreal, would like to change that, and he’s working to train machines to collect, sort and label their own data, so people don’t have to.
Today, Dr. Bachman gives us an overview of the machine learning landscape and tells us why it’s been so difficult to sort through noise and get to useful information. He also talks about his ongoing work on Deep InfoMax, a novel approach to self-supervised learning, and reveals what a conversation about ML classification problems has to do with Harrison Ford’s face.
See more on this and other Microsoft Research podcast episodes: microsoft.com/en-us/research/b...
Свежие видео
7 дней – 1 7780:11
7 дней – 740:38
8 дней – 3 07750:45
12 дней – 21 7723:44
12 дней – 1 6281:35
14 дней – 2 9440:54Случайные видео
298 дней – 2 133 2387:39
302 дня – 238 4430:51
27.10.22 – 143 15113:22
22.10.22 – 225 1415:29
27.03.22 – 4841:52
20.01.17 – 98 7513:35
12 часов – 2800:14
5 дней – 1 2283:25
6 дней – 342 7701:55
7 дней – 237 4465:08
11 дней – 7582:11
13 дней – 4 54916:54
13 дней – 12 7640:16
4 дня – 012:17