Hi, I'm Paul. I teach machines to see and learn.
Data Science & AI student at EPITA (SCIA major), focused on machine learning, deep learning, and computer vision. My models run in daily clinical use at Hôpital des Quinze-Vingts (Paris). Python and C++ are my main languages.
Open to a 6-month internship from February 2027 in Machine Learning / Computer Vision.
Flagship projects
EyeSegmentation
Medical & Research
End-to-end segmentation and classification pipeline for retinal Doppler holography images, now running daily in a hospital diagnostic pipeline.
PythonPyTorchUltralytics YOLO11JupyterHugging Face
View repository →C++ Diffeomorphic Demons
Medical & Research
Modernized a C implementation of the Diffeomorphic Demons medical image registration algorithm into C++, integrating FFTW for a large complexity reduction. Built during the CNRS internship to stabilize retinal video sequences.
C++FFTWCMake
View repository →Neural Network From Scratch
From-scratch
A feedforward neural network written from scratch in C++, no ML libraries, trained on MNIST to classify handwritten digits.
C++CMake
View repository →StockAI
Systems
Detects empty shelf space from a photo, forecasts demand, and has an LLM agent decide whether to restock or order from a supplier.
Azure Custom VisionAzure Machine LearningPythonDockerLLM AgentMCP
View repository →InsightEd
Hackathons
An AI-driven early-warning system for student well-being. K-Means clustering on PISA psychological indicators, Top 10/65 finalist at Hi!ckathon Paris, 2nd on the technical leaderboard.
PythonK-Means ClusteringScikit-learnPandasPCA
Private repository