Mini-course "Learning with Structured Data". Lecture 3.3 (Christoph Lampert)
Автор: ФКН ВШЭ
Загружено: 2016-09-16
Просмотров: 307
Описание:
Structured prediction methods have completely changed the way to solve machine learning problems on the recognition of complex objects with a large number of interdependent components.
The mini-course focuses on an in-depth introduction to the theory and applications of one of today's most popular approaches to solving such problems - discrete probabilistic graphical models.
Using examples from computer vision, we will look at various learning and inference algorithms in graphical models, such as
Confidence propagation (dynamic programming)
Graph cuts
Maximum likelihood estimation
Margin maximisation
Speaker: Professor Christoph Lampert, IST Austria.
Faculty of Computer Science: https://cs.hse.ru/en/
Follow us: / hsefcs , / cs_hse
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке:
![Физически-информированные нейронные сети (PINN) [Машинное обучение с учетом физики]](https://imager.clipsaver.ru/-zrY7P2dVC4/max.jpg)
![Как сжимаются изображения? [46 МБ ↘↘ 4,07 МБ] JPEG в деталях](https://imager.clipsaver.ru/Kv1Hiv3ox8I/max.jpg)
