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
7 days ago 00:03:19 0
NECRO - BEAUTIFUL MUSIC FOR YOU TO DIE TO
1 week ago 00:00:23 0
The Japanese Monk Who Faced a Bear... Without Moving
1 week ago 00:00:24 0
The Most Adorable Monster in Japanese History
2 weeks ago 00:00:23 1
The Human Zoo They Don’t Teach You About
2 weeks ago 00:06:22 2
Почему так мало настоящих христиан? — 6 причин, о которых важно знать
2 weeks ago 00:35:25 0
Теория Большого Взрыва — убита Джеймсом Уэббом?
2 weeks ago 00:00:23 1
She Won the Argument—So They Sealed Her Mouth Shut
2 weeks ago 00:00:20 1
She Fed Her Baby… Dead Mice. Here’s Why.
3 weeks ago 10:13:38 0
Deep Healing Energy | Подборка лечебной музыки из космоса Space Healing music 2025 Bakaev 8,0
3 weeks ago 00:00:23 2
Split-Brain Experiments Prove You’re Not One Person
3 weeks ago 00:00:21 2
Isaac Newton’s Secret Obsession with Alchemy
4 weeks ago 00:00:20 0
The Female Pope They Tried to Erase from History
4 weeks ago 00:00:20 0
The Nobles Who Drank Human Blood: History’s Real Vampires