Going meta: learning algorithms and the self-supervised machine with Dr. Philip Bachman [Podcast]
1 507
12.3
Microsoft Research334 тыс
Следующее
Опубликовано 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
Случайные видео