Université de Bordeaux
Cluster SysNumCluster of Excellence
Cluster of excellence

Seminaire LaBRI - Axe IA: Nathanaël Fijalkow :"Program synthesis in the learning era"- Jeudi 23 janvier 2020 11h Amphithéâtre LaBRI Bât. A30

23/01 : 11h
Last update Monday 20 January 2020

Le LaBRI entame 2020 avec la création d'un groupe IA qui va se réunir régulièrement le jeudi à 11h. L'idée est de prolonger le groupe (à
succès) "Données Massives et Hétéroènes" avec lequel l'intersection thématique est naturellement forte.

Pour le premier seminaire nous aurons le plaisir d'écouter

Nathanaël Fijalkow

 "Program synthesis in the learning era"

Jeudi 23 janvier 2020 11h Amphithéâtre LaBRI Bât. A30

Abstract: Programming by example is a type of program synthesis where the user gives a few pairs of input output and the goal is to find a program satisfying these pairs. I will present a machine learning line of attack for programming by example and discuss the underlying
challenges and the approaches we propose, focussing on two aspects: data generation and search algorithms.

Based on a paper published at AI&STATS2020
(https://arxiv.org/abs/1911.02624) with Judith Clymo (University of Leeds), Haik Manukian (University of California San Diego), Adria Gascon (Google), and Brooks Paige (UCL).

Contact: Laurent Simon

-------------------------------------------------------------------------


  The LaBRI begins 2020 with the creation of an AI group that will meet regularly on Thursdays at 11am. The idea is to extend the (successful) group "Massive and Heterogeneous Data" with which the intersection is naturally large.

For the first seminar, we will have the pleasure to listen to

Nathanaël Fijalkow

 "Program synthesis in the learning era"

Janaury 23th  2020 11h Amphithéâtre LaBRI Bât. A30



Abstract: Programming by example is a type of program synthesis where the user gives a few pairs of input output and the goal is to find a program satisfying these pairs. I will present a machine learning line of attack for programming by example and discuss the underlying
challenges and the approaches we propose, focussing on two aspects: data generation and search algorithms.

Based on a paper published at AI&STATS2020
(https://arxiv.org/abs/1911.02624) with Judith Clymo (University of Leeds), Haik Manukian (University of California San Diego), Adria Gascon (Google), and Brooks Paige (UCL).

Contact: Laurent Simon



TOP