Making intelligence intelligible with Dr. Rich Caruana
1 769
21.1
Microsoft Research334 тыс
Следующее
12.06.18 – 1 2541:35:37Популярные
194 дня – 49856:14
298 дней – 1 5835:28Опубликовано 12 июня 2018, 1:18
Episode 26 | May 30, 2018
In the world of machine learning, there’s been a notable trade-off between accuracy and intelligibility. Either the models are accurate but difficult to make sense of, or easy to understand but prone to error. That’s why Dr. Rich Caruana, Principal Researcher at Microsoft Research, has spent a good part of his career working to make the simple more accurate and the accurate more intelligible.
Today, Dr. Caruana talks about how the rise of deep neural networks has made understanding machine predictions more difficult for humans, and discusses an interesting class of smaller, more interpretable models that may help to make the black box nature of machine learning more transparent.
See more at microsoft.com/en-us/research/b...
In the world of machine learning, there’s been a notable trade-off between accuracy and intelligibility. Either the models are accurate but difficult to make sense of, or easy to understand but prone to error. That’s why Dr. Rich Caruana, Principal Researcher at Microsoft Research, has spent a good part of his career working to make the simple more accurate and the accurate more intelligible.
Today, Dr. Caruana talks about how the rise of deep neural networks has made understanding machine predictions more difficult for humans, and discusses an interesting class of smaller, more interpretable models that may help to make the black box nature of machine learning more transparent.
See more at microsoft.com/en-us/research/b...
Свежие видео
5 дней – 482 7660:57
5 дней – 1 8050:41
9 дней – 71 5600:34
Случайные видео
6 дней – 21710:20
26.09.23 – 99 3888:17
23.11.22 – 104 0139:16
20.04.22 – 30 5356:08
13.07.18 – 119 2471:16
3 дня – 40 81927:39
6 дней – 420 7030:15
11 дней – 1 488 98320:29
12 дней – 7 9824:07
12 дней – 5 3300:47
14 дней – 1005:26
14 дней – 27 4581:00