For their high expressive power and accuracy, machine learning (ML) models are now found in countless application domains. These include autonomous and cyber-physical systems found in high-risk and safety-critical domains, such as healthcare and automotive. These...
Explainable AI has become increasingly relevant, because in many domains, especially safety-critical ones, it is desirable to complement black-box machine learning (ML) models with comprehensible explanations of the models’ predictions. This project focuses on...
Envision a scenario where nanobots travel through the human body, reaching a tumour and deploying their medicinal cargo to eliminate malignant cells while avoiding any unintentional damage. However, before we can successfully employ nanobots to combat cancer, we must...
Abstract: This PhD project aims to address the increasing need for robust privacy-preserving mechanisms in machine learning, particularly focusing on the application of differential privacy within neural networks. With the pervasive use of deep learning in processing...
Our societies are being challenged by a multitude of problems due to deceptive AI. This project will aim to explain the many facets of deceptive AI, that is, its meanings. These facets are historical (the goals of deceptive AI research), behavioral (how machines...
Physical robotic Assistance can often be modelled as a collaborative task in which the goal of both the user and the robot is to complete an assistive task together. However, assistive settings have a lot of particularities that differentiate them from traditional...
Autonomous systems such as robots may become another appliance found in our homes and workplaces. In order to have such systems helping humans to perform their tasks, they must be as autonomous as possible, to prevent becoming a nuisance instead of an aid. Autonomy...
Background: Recent advances in artificial intelligence have led to the development of increasingly sophisticated multi-agent systems that constantly adapt to their changing environment. These systems have wide-ranging applications, from managing traffic networks and...
The Responsible Robotics and AI Lab is open to applications for a PhD in blue sky research at the intersection of robotics and social justice. The project sits at the intersection of Computer Science and Social Science, and it is expected that the successful candidate...
The current state of the art in generative modelling is dominated by neural networks. Despite their impressive performance on many benchmark tasks, these algorithms do not provide tractable inference for common and important probabilistic queries. Moreover, the...
Causal reasoning is essential to decision-making in real-world problems. However, observational data is rarely sufficient to infer causal relationships or estimate treatment effects due to confounding signals. Pearl (2009) proposes a sound and complete formal system...