Speaker: Lirandë Pira
Affiliation: University of Technology Sydney
Abstract
Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. Here, we explore the interpretability of quantum neural networks using local model-agnostic interpretability measures commonly utilized for classical neural networks. Following this analysis, we generalize a classical technique called LIME, introducing Q-LIME, which produces explanations of quantum neural networks. A feature of our explanations is the delineation of the region in which data samples have been given a random label, likely subjects of inherently random quantum measurements. We view this as a step toward understanding how to build responsible and accountable quantum AI models.
About Physics Seminars
The weekly Physics Seminar series focuses on a broad range of physics research within SMP, along with frequent presentations from visiting researchers. Seminars are usually scheduled for 1.00pm on Tuesdays.
The talks are typically more specialised than a colloquium but are often attended by staff and PhD students across a broad range of areas. Speakers are thus encouraged to include introductory material in the talks.
All SMP researchers and HDR students are encouraged to speak. Please email Lewis Williamson to register your interest.
The seminars are open so there is no need to register your attendance.