From automatic differentiation to message passing
4 773
14.1
Microsoft Research321 тыс
Следующее
06.08.19 – 1 0591:06:43Популярные
18.07.22 – 9 1252:00
Опубликовано 6 августа 2019, 16:00
See updated video here: microsoft.com/en-us/research/v...
Automatic differentiation is an elegant technique for converting a computable function expressed as a program into a derivative-computing program with similar time complexity. It does not execute the original program as a black-box, nor does it expand the program into a mathematical formula, both of which would be counter-productive. By generalizing this technique, you can produce efficient algorithms for constraint satisfaction, optimization, and Bayesian inference on models specified as programs. This approach can be broadly described as compiling into a message-passing program.
Automatic differentiation is an elegant technique for converting a computable function expressed as a program into a derivative-computing program with similar time complexity. It does not execute the original program as a black-box, nor does it expand the program into a mathematical formula, both of which would be counter-productive. By generalizing this technique, you can produce efficient algorithms for constraint satisfaction, optimization, and Bayesian inference on models specified as programs. This approach can be broadly described as compiling into a message-passing program.
Свежие видео
3 дня – 3381:34
5 дней – 9 4695:13
8 дней – 50 38027:34
9 дней – 5 8920:55
10 дней – 1 0684:27Случайные видео
138 дней – 1 4180:28
168 дней – 5 9610:16
209 дней – 2190:21
16.08.22 – 25 59243:06
24.11.21 – 9 9572:08
21.10.20 – 4 8509:51
2 дня – 26 28317:08
2 дня – 21 9416:08
2 дня – 33620:04
4 дня – 274 5691:12:32
4 дня – 35 0401:35
6 дней – 21 3890:49
2 дня – 2 3000:13