Image:
Petter Bjørklund

PhD defense: Srishti Gautam

The program will be available shortly. Please check back later.

Srishti Gautam will defend her PhD thesis for the PhD degree in Science at UiT The Arctic University of Norway on Friday March 15th, 2024 at 12:15 PM. The title of her thesis is "Towards Interpretable, Trustworthy and Reliable AI".

The trial lecture and defense will be streamed via the following links

Trial lecture (10:00 AM - 11:00 AM)

PhD defense (12:15 PM - 3 PM)

Summary of the thesis

The field of artificial intelligence recently witnessed remarkable growth, leadingto the development of complex deep learning models that perform exceptionallyacross various domains. However, these developments bring forth critical issues.Deep learning models are vulnerable to inheriting and potentially exacerbatingbiases present in their training data. Moreover, the complexity of these modelsleads to a lack of transparency, which can allow biases to go undetected. Thiscan lead to ultimately hindering the adoption of these models due to a lackof trust. It is therefore crucial to foster the creation of artificial intelligencesystems that are inherently transparent, trustworthy, and fair.This thesis contributes to this line of research by exploring the interpretability ofdeep learning through self-explainable models. These models represent a shifttowards more transparent systems, offering explanations that are integral tothe model’s architecture, yielding insights into their decision-making processes.Consequently, this inherent transparency enhances our understanding, therebyproviding a mechanism to address the inadvertent learning of biases.

Evaluation committee

  • Professor Georgias Leontidis, Chair of Machine Learning, lnterdisciplinary Director of Data and Al, Turing Academic Liaison, Vice-Principals' Office, University of Aberdeen, UK (1. Opponent)
  • Professor Lilja Øvrelid, Language Technology Group, Section for Machine Learning, Department of lnformatics, University of Oslo, Oslo, Norway (2. Opponent)
  • Associate Professor Elisabeth Wetzer, Machine Learning Group, Department of Physics and Technology, UiT (intern member and leader of the committee)