3 papers
cs.AI2021
On Guaranteed Optimal Robust Explanations for NLP Models
Emanuele La Malfa, Agnieszka Zbrzezny, Rhiannon Michelmore +2
We build on abduction-based explanations for ma-chine learning and develop a method for computing local explanations for neural network models in natural language processing (NLP).…
cs.LG2019
Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control
Rhiannon Michelmore, Matthew Wicker, Luca Laurenti +3
Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to thei…
cs.LG2018
Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
Rhiannon Michelmore, Marta Kwiatkowska, Yarin Gal
A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical do…