University of Bamberg
open search form
You are here

Information Systems and Applied Computer Sciences

Chair of Explainable Machine Learning

  1.  University of bamberg
  2. Faculties
  3. Information Systems and Applied Computer Sciences
  4. Subject groups
  5. Applied Computer Science
  6. Chair of Explainable Machine Learning
  7. Team
  8. My Nguyen, M.Sc.

My Nguyen

My NguyenxAILab Bamberg

Research Assistant

M.Sc., Doctoral Candidate

Anschrift:      An der Weberei 5, 96047 Bamberg
Raum:            WE5/04.090

E-mail:            my.nguyen(at)uni-bamberg.de

Consultation hour: 

during lecture times: Thursday 2 p.m. to 3 p.m. in WE5/04.090 (notification per Email recommended)

outside lecture times: by appointment

Biography:

My Nguyen is a PhD candidate at the Chair of Explainable Machine Learning (xAI), Otto-Friedrich-University of Bamberg, since 2025. Her research focuses on anomaly detection in images and videos, alongside broader questions of model and data efficiency, explainability, and robustness. In particular, she investigates how visual anomaly detection models can be realized for critical applications in medical image analysis and food safety, such as automated, AI-driven meat inspection. 

My joined the xAI lab after completing her Master of Science in Computing in the Humanities at the University of Bamberg with a special focus on machine learning, deep learning, and natural language processing. Prior to her doctoral studies, from 2023 to 2025, My worked as a student assistant at the Chair of Explainable Machine Learning, contributing to both teaching and research activities. She supported the courses "Deep Learning" and "Mathematics for Machine Learning" by developing and grading theory and programming exercises.

My pursued her Master’s thesis on enhancing data privacy and model efficiency in Federated Learning. Her work explored the use of Conditional Variational Autoencoders under formal Differential Privacy guarantees, enabling privacy-preserving data sharing and supporting generalization across diverse downstream tasks. The outcomes of her thesis formed the basis for a subsequent research paper, which has been accepted at the MICCAI 2025 conference.

Before completing her Master’s studies, My gained further valuable experience as a research intern at ZEISS in the Imaging and Smart Sensor Systems division. There, she developed deep learning methods for the integration and fusion of foundation models for monocular metric depth estimation. Her work contributed to the development of various visualization technologies, including robust 3D reconstruction in digital microscopy.

Beyond her research in machine learning, My is passionate about linguistics and cultures. She enjoys exploring different countries through their languages and literature just as much as through travel. In her free time, she likes reading, cooking, and working out.