 |
||
|
||
Home > TERATEC FORUM > Workshops > Workshop 6
Wednesday October 14, 2020 - Workshops
Workshop 06 - 11:00 to 12:30
AI in scientific computing : accelerating innovation in industrial and academic domain
Chared by Eric Petit, Research engineer, HPC application specialist, Intel and Michaël Krajecki, Agence de l’Innovation de Défense (AID)
The manufacture of recommended algorithms: a human adventure
In a fierce competitive environment, it is essential to produce a high value proposition in order to retain users. For Deezer, a major player in music streaming., recommendation algorithms are a key element in achieving this.
This presentation will follow the example Flow, an algorithm allowing in real time to produce a totally personalized musical radio that adapts to everyone's tastes and desires. It will endeavor to show how to create, maintain and develop such algorithms in an industrial environment with strong constraints. It will also highlight the collaboration between humans and machines.
There is indeed no magical algorithm but a set of algorithms working in concert, mixing advanced machine learning models, business rules and massive processing of input data. Transforming this underneath complexity to a simple user-friendly product that brings emotions is a huge challenge. And it is only possible by shaping all the development processes with one target in mind: the user’s satisfaction.
 |
Biography : Thomas Bouabca is a Phd in Quantum Physics. During his thesis, he developed algorithms for large scale simulation. After 5 years in the HPC field, he is now director of datascience at Deezer, one of the leaders of music streaming. His teams are in charge to develop the search and recommendation engines in order to improve personalization in the product. |
|---|
Register now and get your badge here
- TERATEC Forum is strictly reserved for professionals.
- Participation to exhibition, conferences and workshops is free (subject to seats available)
- On line registration is obligatory.