Explainable artificial intelligence for scientific discovery: trends and challenges
Our Liverpool Virtual Seminar Series on Data Intensive Science will continue on Tuesday 11th February at 15:00 GMT. The seminar will be given by Simone Scardapane of the University of Rome who will present “Explainable artificial intelligence for scientific discovery: trends and challenges”
Seminars in this series cover R&D outside of the data intensive science CDT’s core research areas and give an insight into cutting edge research in this area. At the end of the talk there will be a Q&A session with the speaker.
About the talk
Explainable AI is a set of tools and techniques to understand and debug neural
network models. In this talk we will overview some of the most common approaches, ranging from input attribution (e.g., saliency maps) to data attribution and to the recent ideas of mechanistic interpretability. We will list open challenges and issues (e.g., polysemanticity), especially in contexts of scientific analysis and discovery in high-energy physics. We will close with ideas and trends for future research in the area
About the speaker
Simone Scardapane is a tenure-track assistant professor in Sapienza University of Rome. His current research focuses on explainability and modularity of neural networks, and their application to scientific domains such as high-energy physics, archaeology, and medicine. He has published more than 130 papers in the field of deep learning in internal journals and conferences (including NeurIPS, ICML, ICLR, and AAAI). Among others, he serves as area chair for NeurIPS and ICLR, and as action editor for Transactions on Machine Learning Research, IEEE Transactions on Neural Networks and Learning Systems, and Neural Networks. He is a junior fellow of the Sapienza School of Advanced Studies, an affiliate researcher at the Italian Institute of Nuclear Physics, and a member of the ELLIS society. He is also involved in the active dissemination of AI in the public via talks and posts. In the past, he served as co-founder and chair of a no-profit association (the Italian Association for Machine Learning) and he also hosted Meetups and podcasts.
How to attend
Participation is free, but you need to register to attend this and other webinars in the series. For more information and how to register please follow this link. Once registered, you will receive the Zoom connection details on the morning of the online seminar.
The seminar details
Speaker: Simone Scardapane (University of Rome)
Seminar title: “Explainable artificial intelligence for scientific discovery: trends and challenges”
Date/Time: Tuesday 11th February at 15:00 GMT