Caroline Mazini Rodrigues

IRISA
263 Av. Général Leclerc
35000 Rennes
I am a postdoctoral researcher at IRISA, focusing on developing low-complexity algorithms for video compression networks to create simpler and interpretable models. I received my PhD from Université Gustave Eiffel, where I worked in the LIGM and LRE laboratories. My research primarily focused on understanding the reasoning processes of Deep Neural Networks, a field commonly referred to as explainable Artificial Intelligence (xAI). I am particularly interested in the challenge of presenting these complex explanations in a way that is easily interpretable for humans.
I am specially intrigued about the cognitive aspects of machine learning and how it can be compared to human learning.
I received my master’s degree from the Institute of Computing (Unicamp), where my focus was on machine learning applied to image analysis in forensics.
Beyond the computer science domain, I’m also interested in studying language mechanisms, including semantics and semiotics. I strongly believe they can inspire us to understand even artificial models.
selected publications
- Bridging Human Concepts and Computer Vision for Explainable Face VerificationIn 2nd Workshop on Bias, Ethical AI, Explainability and the role of Logic and Logic Programming co-located with the 22nd International Conference of the Italian Association for Artificial Intelligence (AI*IA 2023) , 2023