Sami Bourouis
Papers
1
Total Citations
2
H-Index
1
About
Sami Bourouis is a leading researcher in statistical machine learning and computer vision, with a particular focus on mixture models and their applications in image processing and pattern recognition. His work centers on developing robust probabilistic frameworks—such as Gamma mixture models—that effectively handle complex, non-Gaussian data distributions. Bourouis’s most cited paper, "Expectation propagation learning of finite and infinite Gamma mixture models and its applications" (2023, 2 citations), introduces a novel expectation propagation approach for learning both finite and infinite mixture models, enabling more accurate and scalable inference in real-world scenarios. This contribution is pivotal for tasks like image segmentation, object detection, and medical imaging, where data often exhibit heavy-tailed or skewed characteristics. Beyond this, Bourouis has advanced the field by integrating Bayesian nonparametrics with variational inference, offering flexible solutions for high-dimensional data. His research has garnered attention for its practical impact, with applications ranging from remote sensing to biomedical analysis. Bourouis’s work continues to inspire new directions in adaptive learning algorithms, making him a notable figure in the intersection of statistical modeling and applied machine learning.
Research Focus
Key Achievements
Top Papers
- 1