From automatic differentiation to message passing

preview_player
Показать описание
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.

Рекомендации по теме
Комментарии
Автор

Can you guys put presenters’ names in video titles?

parkatip
Автор

This was the only video that made me understand how autodiffworks.

gzitterspiller
Автор

Any code samples for gradient descent as a message-passing algorithm?

vikranj