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...
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...
I am currently looking into defining an information-theoretic measure of the “effectiveness” of explanations in a communicative multiagent setting. This involves setting up the problem of generating explanations as a two-player cooperative game in which rewards are...
My PhD project is on value alignment; that is, how can we ensure that AI agents are beneficial to society rather than harmful. To this end, I’m looking at how AI agents may reason about values like humans do. I’m especially interested in this in...
PhD Project: The value alignment problem is concerned with designing artificially intelligent systems which behave according and with respect to human values. A critical component of this problem is shaped by the fact that humans are not always consistent in which...
My PhD project focuses on explaining black-box classifications. More precisely on how logical rules can accurately represent the behaviour of a neural network and then be used to explain that behaviour. I chose to do my PhD as part of this CDT because my project...
During my masters I trained a population of LSTMs to trade profitably in an automated stock market. I worked as a ‘Research Analyst’ for a financial services firm between my masters and PhD, however the experience was very different to that of academic...