EP-IT Data Science Seminars

Problem solving as a translation task

Name: Problem solving as a translation task
Start: 2024-01-31T11:00:00+01:00
End: 2024-01-31T12:00:00+01:00
Location: CERN

by Francois Charton (META AI)

Wednesday 31 Jan 2024, 11:00 → 12:00 Europe/Zurich

503/1-001 - Council Chamber (CERN)

503/1-001 - Council Chamber

CERN

162

Show room on map

Description

Neural architectures designed for machine translation can be used to solve problems of mathematics, by considering that solving amounts to translating the problem, a sentence in some mathematical language, into its solution, another sentence in mathematical language. Presenting examples from symbolic and numerical mathematics, and theoretical physics, I show how such techniques can be applied to develop AI for Science, and help understand the inner workings of language models.

Francois Charton is a research engineer in Meta AI, working on applications of language models to mathematics and science. He is a former student of Ecole Polytechnique, and ENSAE (Ecole Nationale de la Statistique et de l'Administration Economique). He has been in Meta since 2019, and had a career in industry prior to that.

Coffee will be served at 10:30.

Organised by

M. Girone, M. Elsing, L. Moneta, M. Pierini
Event co-organised with IML coordinators as part of the 6th IML Workshop (https://indico.cern.ch/event/1297159/)

Webcast

There is a live webcast for this event

Contact

EP-seminars.colloquia@cern.ch

Choose timezone

Problem solving as a translation task

by Francois Charton (META AI)

503/1-001 - Council Chamber

CERN