Charles Vin

• Conducted extensive literature review on state-of-the-art methods in self-supervised learning (SSL) applied to Satellite Image Time Series (SITS).
• Reproduced and benchmarked baseline models to ensure robust performance comparisons.
• Developed and implemented an innovative image retrieval pretext task utilizing a specialized hierarchical loss function to train SSL models on SITS data.
• Actively participated in research lab activities.

• Frontend development of an e-commerce website.
• Implementation of a backend using Docker and creation of a CI/CD pipeline for the frontend.
• Configuration of a mail server and a newsletter manager.
• Effective communication with non-technical individuals to explain constraints and possibilities.
• Project management within specific deadlines.

• Development of a convolutional neural network for insect classification.
• Use of gradient-based approaches and the LIME and SHAP frameworks.
• Takeover, adaptation and documentation of the project.
• Experiences monitoring and evaluation of different models with WandB.

• Processed raw EMG/ECG signals and AXCPT task data.
• Employed data visualization techniques.
• Utilized statistical tests to uncover group differences.
• Delivered presentations and reports to communicate findings effectively.

• Developed an algorithm to recommend sports categories to practice based on motivation profile, sport tolerance, and activity level.
• Explored various approaches including Neural Networks (NN), K-Prototype, Discriminant Function Analysis (DFA) and XGBoost.
• This contract marked my inaugural foray into the realm of Machine Learning.
• Conducted some data visualization on the survey data.
• Data were coming from approximately 2000 survey responses which included the following psychological test :
  • Physical Activity and Leisure Motivation Scale (PALMS): Discerne factors driving participation in sports, such as psychological factors or appearance.
  • Sport Tolerance (PRETIE-Q): Assesses the participant's ability to persevere in high-intensity physical activities, even when uncomfortable.
  • Activity Level (IPAC): Categorize participants as high or low activity level.
  • A comprehensive list of sports practised by each participant.

• Study of the trade-off between observation and action in reinforcement learning (subject details)
• Understanded, independently, a cutting-edge problem in reinforcement learning.
• Demonstrated perseverance and determination in the face of technical challenges.
• Implemented an experimental plan.

• Verification and validation of MATLAB code processing thermal camera data to ensure compliance with the researcher's requirements for publication.
• Various computer-related tasks

• Assessed the reliability of a new model of eye-tracking glasses that were using machine learning.
• Wrote a user manual for these glasses.
• Data processing and visualization for other researchers on the platform.

Relevant courses:

• Image and signal processing
• Mathematics for ML (statistics/probability, Markov Chain, ...)
• Databases: SQL, XML, JSON, distributed databases
• Machine Learning: classification, neural networks, decision trees
• Natural language processing, information retrieval
• Opening courses from Master of Mathematics: statistical learning and convex optimization.

Grade: Highest Honours

Relevant courses:

• Decision statistics: practical work in R.
• Probability and measurement theory
• Cognitive science

Relevant academic projects:

• Bayesien Tweet Classifier: "Positive" or "Negative" tweets classifier
• Basic ML algorithm from scratch: KNN, KMean, linear/polynomial regression