My PhD project is about improving the robustness and transparency of black box machine learning (ML) models. We are planning to do that by making ML models respect imparted and discovered causal knowledge to then use this as the basis of argumentative...
My PhD project focuses on the exploration and analysis of natural language texts, specifically of philosophical debates on society’s ethical and moral issues, through argument schemes and critical questions. The aim is to develop a new corpus which will enable...
My PhD project focuses on verification of AI systems, in particular neural networks. Nowadays, a broad variety of systems employ AI algorithms to perform certain tasks. However, these models do not lend themselves to traditional verification methods, and for some...
I focus on developing new methods to provide provable formal guarantees on neural network behaviour. Specifically, I have interests in geometric robustness and Lipschitz-based local and global robustness for neural network verification. While a standalone PhD is...
My PhD project is about developing human-in-the-loop explainability framework for CNNs. My final year project during undergraduate studies motivated me to pursue a career in the field of interpretable or explainable AI. This CDT program brings out the aspect...
My PhD project focuses on how we can trust agent-based models to inform public policy using validation, formal verification and computational acceleration. The application of this research is misinformation on social media. When choosing the direction for my...
My background is in pure math and I’m excited to combine it with philosophy and psychology in my PhD. In particular, I am interested in psychology-inspired AI. Insight into Theory of Mind, decision-making, reasoning, learning and language understanding in humans can...
Undergraduate Qualification: BSc in Computer Science, University of Vienna Masters Qualification: MSc in Computing (AI Specialism), Imperial College London In my PhD I am trying to combine subsymbolic (e.g. neural networks) and symbolic AI...
Undergraduate Qualification: BA in Sociology and Social Policy, Charles University Masters Qualification: Big Data and Digital Futures, University of Warwick My PhD project focuses on the interaction between AI systems and users. In particular, I am interested in...
Undergraduate Qualification: BSc in Physics, Imperial College London Masters Qualification: Masters in Robotics and Computation, University College London My PhD project explores the evolution of many body systems (crowds, swarms, particles etc). I aim to...
Currently, I’m working on the safe exploration problem in reinforcement learning. In particular, I look at ways to use verification techniques to distinguish safe exploration strategies from unsafe ones. In the long run, I’m interested in extending safe...
My PhD project is verification of Neural Networks. Research into safe and trusted AI is sorely lacking, especially now that AI is being implemented in more and more safety-critical applications. In the STAI CDT I hope that I can contribute to the field and make a...
