CV

About me

I am a passionate Machine Learning Engineer and PhD Student specializing in Generative Deep Learning. My unique position bridges industrial applications and academic research, allowing me to drive challenging projects and propose innovative solutions to real-world problems.

Currently pursuing my PhD in collaboration between Paul Wurth Luxembourg and RPTU Kaiserslautern, I focus on developing novel deep learning architectures for domain mapping in multivariate time series. My research has direct applications in industrial process optimization, particularly in metallurgical operations.

With a strong background in both theoretical foundations and practical implementations, I am dedicated to advancing the field of AI while solving real-world problems. My work combines rigorous scientific methodology with innovative engineering solutions.

Education

PhD in Generative Deep Learning

2021 - Now

Paul Wurth Luxembourg & RPTU Kaiserslautern

Thesis topic: Deep Domain Mapping for Multivariate Time Series.

Thesis directors: Dr. lr. Cédric Schockaert & Prof. Dr. Didier Stricker.

Engineer Degree in Artificial Intelligence

2015 - 2020

Higher Institute of Electronics and digital science (ISEN-Lille)

Experiences

PhD Student

2023 - Now

Paul Wurth Luxembourg & RPTU Kaiserslautern

Thesis topic: Deep Domain Mapping for Multivariate Time Series.

Thesis directors: Dr. lr. Cédric Schockaert & Prof. Dr. Didier Stricker.

Click for more details...

Industrial Context

Collaboration with Paul Wurth to release a new AI-based product for blast furnace operations.

Research Goals:

Development of generative deep learning models for multivariate time series
More robust models for blast furnace operations
Anomaly detection in blast furnace operations

Key Technologies

Python,TensorFlow, MLflow
Generative Adversarial Networks (GAN), Deep Representaiton Learning
AdvancedTime series analysis and signal processing
Linux, Docker and system administration

Research & Development Specialist

2020 (6months)

Interdisciplinary Centre for Security, Reliability and Trust (SNT) - Kirchberg

Development and deployment of machine learning solutions for industrial applications.

Achievements

Assist the scientist in research projects.

Main Tasks:

Web development: Assist the Development of the COVID cases Simulator
Natural Language Processing: Unsupervised classification of emails
Android Security: Static analysis of the Android binary part of application

Technologies Used

React for the web application
Python, Scikit-learn, Pandas, NumPy...
Ghidra for Android reverse engineering

Deep Learning Internship

2020 - (6 months)

Paul Wurth Luxembourg

Research internship on deep learning for computer vision applications.

Skills Acquired

Accomplished 3 r&D projects (instead of 1 as expected).

Projects:

Unsupervised anomaly detection applied of the Bell less top signals.
Heart measurements feature extraction using a home made 3D comvolutional layer (not implemented in Tensorflow at this time).
Hot Metal Temperature Prediction.

Machine Learning Internship

2019 - (3 months)

Wavely

R&D projects:

Unsupervised clustering to elaborate a tool to speed-up the manual Labeling process.

Tasks:

Signals processing and feature extraction.
Data Preparation and preprocessing.
Model training and evaluation.

Skills

Techniques

Python LaTeX Git TensorFlow MLflow Linux Docker System administration

Research

Methodology Scientific writing Presentation Supervised learning Unsupervised learning Semi-Supervised learning Representation learning

Languages

French (native) Anglais (B2)

Papers

"MISTI: Multi-Style Transfer for Multivariate Time Series" (Accepted, EUSIPCO 2025)
"Which Time Series Domain Shifts can Neural Networks Adapt to?" (Accepted, EUSIPCO 2024)
"Unsupervised Image-to-Image Translation: A Review" (Accepted, MDPI)
"JuCify: a step towards Android code unification for enhanced static analysis" (Accepted, ICSE 2022)
"Mts-cyclegan: An adversarial-based deep mapping learning network for multivariate time series domain adaptation applied to the ironmaking industry" (ArXiv)

Henri Hoyez