Incentive-aware digital twins for finance

Modern financial markets represent fertile soil for AI systems. As of October 2019, at least two thirds of the UK financial services companies use AI, with its growing adoption in trading, risk management and pricing. Should the regulator trust the AI technology that...

Verification of Matching Algorithms for Social Welfare

Matching is a fundamental problem in combinatorial optimisation with multiple applications in AI, like in belief propagation [10], multi-agent resource allocation algorithms [6], and constraint solving [16], and in economics, like the stable marriage problem [17] and...

Causal Temporal Logic

Temporal logic (TL) is arguably the primary language for formal specification and reasoning about system correctness and safety. They enable the specification and verification of properties such as “will the agent eventually reach the target while avoiding...

Improving Robustness of Pre-Trained Language Models

Recent efforts to Natural Language Understanding (NLU) have been largely exemplified in tasks such as natural language inference, reading comprehension and question answering. We have witnessed the shift of paradigms in NLP from fine-tuning a large-scale pre-trained...

Explanations of Medical Images

We developed a framework for causal explanations of image classifiers based on the principled approach of actual causality [1] and responsibility [2], the latter pioneered by Dr Chockler. Our framework already resulted in a number of publications in top-ranked...

Multiple Explanations of AI image classifiers

We developed a framework for causal explanations of image classifiers based on the principled approach of actual causality [1] and responsibility [2], the latter pioneered by Dr Chockler. Our framework already resulted in a number of publications in top-ranked...

Integrating Sub-symbolic and Symbolic Reasoning for Value Alignment

An important long-term concern regarding the ethical impact of AI is the so called ‘value alignment problem’; that is, how to ensure that the decisions of autonomous AIs are aligned with human values. Addressing this problem, as well as the broader...

Learning and deploying safe and trustworthy models of data provenance

Our modern lives are increasingly governed by ubiquitous AI systems and an abundance of digital data. More and more products and services are providing us with better tools and recommendations for our professional, personal, and entertainment activities. With the...

Generative modelling with neural probabilistic circuits

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 queries, e.g. marginalization and...