The Science of Cause and Effect: From Deep Learning to Deep Understanding
Judea Pearl (UCLA)
Theoretically Speaking
What does it mean to “understand” a phenomenon, a domain, or a situation?
Machine learning systems have long been labeled “opaque,” “black boxes,” or plain “dumb” for not “understanding” the purpose or the implications of their predictions. But what does it take to qualify as an “understander,” and what computational capacities are needed to meet these requirements?
In this talk, Judea Pearl will propose a formal definition of “understanding” as the capacity to answer questions of three types: predictions, actions, and imagination. He will describe a computational model, a language, and a calculus that facilitate reasoning at these three levels, and demonstrate how features normally associated with understanding follow from this model. They include generating explanations, generalization across domains, integrating data from several sources, recovery from missing data, and more. P
2 views
8
2
4 weeks ago 00:11:28 1
True Facts: Bees That Play With Balls And Do Math!
4 weeks ago 00:05:03 1
Mix SILICONE and ACETONE! The results were shocking because they were so unexpected
4 weeks ago 00:03:21 1
Музыка Для Души ,,ЛИСТ ОСЕННИЙ,, Музыка Сергей Грищук #МУЗЫКА #КРАСИВАЯМУЗЫКА
4 weeks ago 00:01:00 1
Army Sergeant Major Shocks Soldiers with New Standards
4 weeks ago 00:59:34 7
Большое путешествие на край Вселенной.
1 month ago 00:53:47 2
Myths BUSTED! Brave German Journalist EXPOSES Ukraine/NATO War Lies.