Simon Bernard
- Equipe Apprentissage (LITIS - DocApp)
- Université de Rouen Normandie (UNIROUEN)
- Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes (LITIS)
Présentation
I am an associate professor (Maître de Conférence) at the University of Rouen Normandy, and a member of the Machine Learning team of the LITIS lab. (UR 4108). I am also a member of the Data, Learning, Knowledge group in the CNRS Research Federation NormaSTIC (FR 3638). My research focuses on machine learning, and more specifically on ensemble learning and deep learning methods. In recent years, my work has focused mainly on multi-view/multimodal learning and outlier/anomaly detection. Recently, I've also taken a keen interest in machine learning for physics, with operator learning methods and/or physic-informed learning methods. I teach computer science and machine learning at the Faculty of Science et Techniques of the University of Rouen Normandy, to bachelor and master students. Today, I mostly teach machine learning and web programming to students of the Data Science master's program.
Domaines de recherche
Publications
Publications
TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel ConditioningInternational Conference on Learning Representations (ICLR), 2025, Singapour, France. ⟨10.48550/arXiv.2410.09306⟩ |
|
|
|
Domain Translation via Latent Space Mapping2023 International Joint Conference on Neural Networks (IJCNN), Jun 2023, Gold Coast, Australia. pp.1-10, ⟨10.1109/IJCNN54540.2023.10191215⟩ |
|
|
A Novel Random Forest Dissimilarity Measure for Multi-View Learning2020 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan, France. pp.1344-1351, ⟨10.1109/ICPR48806.2021.9412961⟩ |
|
|
Dynamic Voting in Multi-view Learning for Radiomics ApplicationsIAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR 2018) and Structural and Syntactic Pattern Recogntion (SSPR 2018), S+SSPR, Aug 2018, Beijing, China. pp.32-41, ⟨10.1007/978-3-319-97785-0_4⟩ |
|
|
Dissimilarity-based Representation for Radiomics ApplicationsFirst International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI'2018), May 2018, Montréal, Canada. pp.53--58 |
Pondération dynamique en apprentissage multi-vues pour des applications radiomicsConférence sur l’apprentissage automatique (CAp), Jun 2018, Rouen, France |
|
|
|
Improve the Performance of Transfer Learning Without Fine-Tuning Using Dissimilarity-Based Multi-view Learning for Breast Cancer Histology ImagesInternational Conference Image Analysis and Recognition (ICIAR), Jun 2018, Póvoa de Varzim, Portugal. pp.779-787, ⟨10.1007/978-3-319-93000-8_88⟩ |
|
|
ROC-based cost-sensitive classification with a reject option23rd IEEE International Conference on Pattern Recognition (ICPR), Dec 2016, Cancun, Mexico. ⟨10.1109/ICPR.2016.7900146⟩ |
|
|
Apprentissage multiclasse en environnement incertainSociété Francophone de Classification, Sep 2014, Rabat, Maroc |
A new random forest method for one class classificationJoint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), Nov 2012, Hiroshima, Japan. pp.282-290 |
|
A random forest based approach for one class classification in medical imaging3rd MICCAI International Workshop on Machine Learning in Medical Imaging (MLMI), 2012, Nice, France. pp.250-257 |
|
|
|
A Study of Strength and Correlation in Random ForestsInternational Conference on Intelligent Computing, Aug 2010, Changsha, China. pp.186-191, ⟨10.1007/978-3-642-14831-6_25⟩ |
|
|
Influence of Hyperparameters on Random Forest AccuracyInternational Workshop on Multiple Classifier Systems (MCS), Jun 2009, Reykjavik, Iceland. pp.171-180, ⟨10.1007/978-3-642-02326-2_18⟩ |
|
|
Une étude sur la paramétrisation des Forêts Aléatoires11ème Conférence francophone sur l'Apprentissage Artificiel (CAp), May 2009, Hammamet, Tunisie. pp.81-92 |
|
|
Towards a better understanding of random forests through the study of strength and correlation5th International Conference on Intelligent Computing (ICIC), Sep 2009, Ulsan, South Korea. pp.536-545, ⟨10.1007/978-3-642-04020-7_57⟩ |
|
|
On the selection of decision trees in Random ForestsIEEE International Joint Conference on Neural Networks (IJCNN), Jun 2008, Atlanta, United States. pp.302-307, ⟨10.1109/IJCNN.2009.5178693⟩ |
|
|
De la sélection d'arbres de décision dans les forêts aléatoires10ème Colloque International Francophone sur l'Ecrit et le Document (CIFED), Oct 2008, Rouen, France. pp.163-168 |
|
|
Etude de l'influence des paramètres sur les performances des forêts aléatoires10ème Colloque International Francophone sur l'Ecrit et le Document (CIFED), Oct 2008, Rouen, France. pp.207-208 |
|
|
Forest-RK: A New Random Forest Induction Method4th International Conference on Intelligent Computing (ICIC), Sep 2008, Shanghai, China. pp.430-437, ⟨10.1007/978-3-540-85984-0_52⟩ |
|
|
Using Random Forests for Handwritten Digit Recognition9th IAPR/IEEE International Conference on Document Analysis and Recognition (ICDAR), Sep 2007, Curitiba, Brazil. pp.1043-1047, ⟨10.1109/ICDAR.2007.4377074⟩ |
|
|
Random Forest for Dissimilarity-based Multi-view LearningHandbook of Pattern Recognition and Computer Vision, 6, World Scientific, pp.119-138, 2020, ⟨10.1142/9789811211072_0007⟩ |
|
|
Forêts Aléatoires: De l'Analyse des Mécanismes de Fonctionnement à la Construction DynamiqueApprentissage [cs.LG]. Université de Rouen, 2009. Français. ⟨NNT : ⟩ |