Logo

Mathematical Sciences Research Institute

Home » DDC Junior Seminar: Model theory, automata, and learning

Seminar

DDC Junior Seminar: Model theory, automata, and learning December 08, 2020 (09:00 AM PST - 10:00 AM PST)
Parent Program:
Location: MSRI: Online/Virtual
Speaker(s) James Freitag (University of Illinois at Chicago)
Description

To participate in this seminar, please register here: https://www.msri.org/seminars/25206

The seminar will feature research talks by the six postdoctoral scholars appointed to the Fall 2020 DDC program, along with talks by students and other pre-tenure researchers associated with this program.  Since seminar attendees will have disparate backgrounds, we plan that these talks will not be too advanced, nor will they assume substantial background knowledge.  Our postdocs include number theorists, model theorists, and computable structure theorists, and talks can be expected to span all of these areas.

 

Video

Model Theory, Automata, And Learning

Abstract/Media

To participate in this seminar, please register here: https://www.msri.org/seminars/25206

Abstract: Over the last several years, new connections between model theoretic notions of tameness and a variety of settings for machine learning have emerged. In this talk we will survey some of these connections, discussing equivalence queries, membership queries, and private learning. Recently, new effective algorithms have emerged from the connection as well, and we will illustrate the interesting case of learning automata. 

No Notes/Supplements Uploaded

Model Theory, Automata, And Learning

H.264 Video 25162_28660_8674_Model_Theory__Automata__and_Learning.mp4