My research field is centered on time series classification and interpretable machine learning. I have mainly worked on the interpretability for a CNN, which allows to learn interpretable shapelets that are useful to explain a decision.
Ph.D. thesis: Interpretable shapelets for anomaly detection in time series
University of Rennes | Rennes, France | April 2018 - ??
Inria/IRISA Laboratory, LACODAM Team
Supervisors: Prof. Elisa FROMONT, Dr. Simon MALINOWSKI, Dr. Romain TAVENARD, and Dr. Rémi EMONET.
University of Orléans | Orléans, France | 2014 - 2017
Master thesis: Airfoil optimization based on Class Shape Transformation (CST) method
Beijing Institute of Technology | Beijing, China | 2010 - 2014
Major: Vehicle engineering
Seminar: Obelix Team (IRISA)
UBS | Vannes, France | March 18, 2019
Learning interpretable shapelets for time series classification through adversarial regularization
Introduction to object-oriented programming with python: corrections
ENSAI | Rennes, France
Tutorial on data structures, functions, classes, modules
Two groups of first year students (35 students)
Lead instructor: Mohamed Graiet
42 hours laboratory courses
Yichang Wang, Rémi Emonet, Elisa Fromont, Simon Malinowski, and Romain Tavenard, “Adversarial Regularization for Explainable-by-Design Time Series Classification”, in ICTAI 2020 (32th International Conference on Tools with Artificial Intelligencee). [PDF]
Yichang Wang, Rémi Emonet, Elisa Fromont, Simon Malinowski, Etienne Menager, Loïc Mosser, and Romain Tavenard, “Learning Interpretable Shapelets for Time Series Classification through Adversarial Regularization”, in CAP 2019 (Conférence sur l'Apprentissage automatique). [PDF (in French)]
Yichang Wang, Yanfeng Gao, Pascale Magaud, Lucien Baldas, Christine Lafforgue, and Stéphane Colin, “Inertial migration of neutrally buoyant particles in square channels at high Reynolds numbers”, in μFlu 2018 (5th European Conference on Microfluidics). [PDF]