Cecilia Panigutti
Data Science Ph.D. Student (Cycle 33)
Bio:
Before starting my Ph.D., I worked for two years as a Junior Data Scientist for aizoOn, a technology consulting company based in my hometown, Torino. In particular, I used to work as a consultant in an industrial vehicle manufacturing company. During these years, I had the opportunity to deal with real-world Data Science problems. I also had the chance to put into practice the main Machine Learning techniques that I learned during my master’s studies in Physics of Complex Systems.
While working side to side with the end-users of the tools I was developing, I realized how important it was to be able to explain the model’s reasoning to gain the trust of the final decision-makers. I became very passionate about the topic of interpreting Machine Learning models’ decisions.
Research Interest:
My research interest is on Explainable Machine Learning techniques. In particular, my focus is on developing post-hoc interpretability methods that separate the explanation from the black-box model (agnostic approach). I'm also interested in causal inference, and in the ethical and legal implications of AI use in safety-critical domains such as health-care.
Affiliation:
Email:
Skype:
GitHub:
Twitter:
Google Scholar:
Office:
Address:
Building:
Floor:
Room:
Bibliography
2020
-
, “Doctor XAI: an ontology-based approach to black-box sequential data classification explanations”, in Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020.
2019
-
, “Explaining multi-label black-box classifiers for health applications”, in International Workshop on Health Intelligence, 2019.
2017
-
, “Assessing the use of mobile phone data to describe recurrent mobility patterns in spatial epidemic models”, Royal Society open science, vol. 4, p. 160950, 2017.
