Uczenie maszynowe i logika: szybkie i wolne myślenie

jk — Mon, 12 Dec 2022 17:34:57 +0000

Machine Learning and Logic: Fast and Slow Thinking jk Mon, 12/12/2022 - 18:38

Type

Lecture

Date

Mon, 12/12/2022 - 16:00

Building

Building of Faculty of Mathematics and Information Science, WUT

Room no.

329

Speaker

Prof. Moshe Y. Vardi

Attachments

Lecture slides

Computer science seems to be undergoing a paradigm shift. Much of earlier research was conducted in the framework of well-understood formal models. In contrast, some of the hottest trends today shun formal models and rely on massive data sets and machine learning.

A cannonical example of this change is the shift in AI from logic programming to deep learning.

I will argue that the correct metaphore for this development is not paradigm shift, but paradigm expansion. Just as General Relativity augments Newtonian Mechanics, rather than replace it — we went to the moon, after all, using Newtonian Mechanics — data-driven computing augments model-driven computing. In the context of Artificial Intelligence, machine learning and logic correspond to

the two modes of human thinking: fast thinking and slow thinking.

The challenge today is to integrate the model-driven and data-driven paradigms. I will describe one approach to such an integration — making logic more quantitative.

Slajdy z wystąpienia Prof. W. Ducha

jk — Wed, 22 Nov 2017 12:44:27 +0000

Slides from Prof. W. Duch's lecture jk Wed, 11/22/2017 - 13:44

Slides used during the lecture were published on a page presenting a lecture's abstract.

Intelligent systems - theory, practice, challenges

Uczenie maszynowe i logika: szybkie i wolne myślenie

Slajdy z wystąpienia Prof. W. Ducha