Shelvia Wongso

Researcher in Information Theory for Machine Learning.

prof_pic.jpg

I am currently pursuing a PhD at the National University of Singapore, specializing in Artificial Intelligence (AI), under the supervision of Professor Mehul Motani. I am interested in using information theory to understand deep neural networks. My research areas in deep learning include generalization, explainability, fairness, robustness, uncertainty quantification and privacy, all of which are important to build safe and trustworthy AI models.

Other interests: particle physics and neuroscience
Hobbies: taking walks, reading books, and journaling

Contact: shelvia.w@u.nus.edu

News

May 7, 2024 My abstract is accepted at Recent Results Poster Session of the ISIT 2024. More details about it soon!
Apr 14, 2024 My paper is accepted at ISIT 2024 Workshop on Information-Theoretic Methods for Trustworthy Machine Learning. More details about it soon!

Latest Posts

Selected Publications

  1. Pointwise Sliced Mutual Information for Neural Network Explainability
    Shelvia Wongso, Rohan Ghosh, and Mehul Motani
    In IEEE International Symposium on Information Theory, (ISIT), 2023
  2. Using Sliced Mutual Information to Study Memorization and Generalization in Deep Neural Networks
    Shelvia Wongso, Rohan Ghosh, and Mehul Motani
    In International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
    Oral Presentation at AISTATS (Top 1.9% of Submitted Papers).
  3. Understanding Deep Neural Networks Using Sliced Mutual Information
    Shelvia Wongso, Rohan Ghosh, and Mehul Motani
    In IEEE International Symposium on Information Theory, (ISIT), 2022