Grégoire Hornung

data scientist, phd in physics, bayesian zealots

Peut se déplacer à Bruxelles

  • 50.8503396
  • 4.351710300000036
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Grégoire.
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Grégoire.

Localisation et déplacement

Localisation
Bruxelles, Belgique
Peut travailler dans vos locaux à
  • Bruxelles et 50km autour

Vérifications

  • E-mail vérifié

Langues

Catégories

Compétences (8)

Grégoire en quelques mots

Big science inevitably goes together with big data.
Based on this observation, I've decided to fully commit myself in the development of machine learning and advanced data analysis tools such as to pioneer the deployment of data science solutions in one of the world's largest research program, the quest for mastering fusion energy.

Aside from my research activities, I regularly participate to data science competitions organized by private companies. There, I can collaborate with people from different backgrounds. Indeed, I am convinced that diversity, open-mindedness, and interdisciplinary create conductive conditions for the development of ground-breaking solutions.

Expériences

University of Ghent

Centres de recherche

Data scientist

Gand, Belgique

novembre 2013 - Aujourd'hui

I am a member of the advanced data analysis group within the nuclear fusion research unit.
We aim to contribute to the development of fusion energy by applying state-of-the-art techniques from machine learning and pattern recognition.

My work covers various topics such as:
-- Machine Learning: classification and prediction of plasma regime in high dimensional space using supervised learning techniques
- - Data Mining: design and mining of turbulence measurements databases in order to reveal hidden patterns in nuclear fusion experiments
- - Statistical Inference: improving the measurement of plasma turbulence with Bayesian probability and inverse problem theory.
-- Computer vision: video tracking of non-rigid propagating objects in complex environment (follow the link below to see our algorithm in action).
  • Matlab
  • Bayesian inference
  • Inverse problem
  • Nonlinear time series
  • Markov Chain Monte Carlo
  • information geometry
  • Spark
  • python
  • Voir plus de compétences

Euroclear

Banque & assurances

Text mining

Bruxelles, Belgique

mai 2016 - juin 2016

Information extraction on unstructured “terms and conditions” documents associated to the settlement of various bonds and securities.

Procter and Gamble - Procter and Gamble

Mode & cosmétiques

Improving the sustanaibility of soap manufacturing

Bruxelles, Belgique

février 2016 - mars 2016

Design of an interactive dashboard for the analysis of real-time and historical energy consumption. Identification of unexpected correlations between different production units.

Recommandations externes

Formations

charter modal image

Notre succès est une oeuvre collective

Contribuez à cette réussite et au sérieux de la communauté en signant la charte du freelance Malt.

Signer la charte