Machine teaching with Dr. Patrice Simard
2 005
15.2
Microsoft Research333 тыс
Следующее
29.05.19 – 1 24356:21Популярные
338 дней – 26432:52
Опубликовано 29 мая 2019, 15:00
Episode 78 | May 29, 2019
Machine learning is a powerful tool that enables computers to learn by observing the world, recognizing patterns and self-training via experience. Much like humans. But while machines perform well when they can extract knowledge from large amounts of labeled data, their learning outcomes remain vastly inferior to humans when data is limited. That’s why Dr. Patrice Simard, Distinguished Engineer and head of the Machine Teaching group at Microsoft, is using actual teachers to help machines learn, and enable them to extract knowledge from humans rather than just data.
Today, Dr. Simard tells us why he believes any task you can teach to a human, you should be able to teach to a machine; explains how machines can exploit the human ability to decompose and explain concepts to train ML models more efficiently and less expensively; and gives us an innovative vision of how, when a human teacher and a machine learning model work together in a real-time interactive process, domain experts can leverage the power of machine learning without machine learning expertise.
See more at microsoft.com/en-us/research/b...
Machine learning is a powerful tool that enables computers to learn by observing the world, recognizing patterns and self-training via experience. Much like humans. But while machines perform well when they can extract knowledge from large amounts of labeled data, their learning outcomes remain vastly inferior to humans when data is limited. That’s why Dr. Patrice Simard, Distinguished Engineer and head of the Machine Teaching group at Microsoft, is using actual teachers to help machines learn, and enable them to extract knowledge from humans rather than just data.
Today, Dr. Simard tells us why he believes any task you can teach to a human, you should be able to teach to a machine; explains how machines can exploit the human ability to decompose and explain concepts to train ML models more efficiently and less expensively; and gives us an innovative vision of how, when a human teacher and a machine learning model work together in a real-time interactive process, domain experts can leverage the power of machine learning without machine learning expertise.
See more at microsoft.com/en-us/research/b...
Свежие видео
6 дней – 88 70735:06
9 дней – 1 0070:26
15 дней – 1 5311:13
17 дней – 42 3506:49
98 дней – 6 1960:18Случайные видео
147 дней – 21 86751:26
220 дней – 2621:30
228 дней – 1 57133:08
31.08.22 – 237 6360:22
30.03.20 – 1 074 01118:41
36 дней – 3 4250:28
7 дней – 6 4251:00
9 дней – 10 021 82212:03
10 дней – 1 247 55127:25
10 дней – 3 1834:06
15 дней – 14 1871:26
17 дней – 12 4871:41
19 дней – 20 0087:34
21 час – 3692:17
6 дней – 4770:52