• Fast Reinforcement Learning using Memory-Augmented Neural Networks

    Project ID: STAI-CDT-2023-KCL-27
    Themes: Norms, Reasoning
    Supervisor: Yali Du, Albert Meroño Peñuela

    Reinforcement learning resembles human learning with intelligence accumulated through experiment. To attain expert human-level performance on tasks such as Atari video games or chess, deep RL systems have required many...

    Read more

  • Extracting interpretable symbolic representations from neural networks using information theory and causal abstraction

    Project ID: STAI-CDT-2023-IC-4
    Themes: Logic, Norms, Reasoning
    Supervisor: Pedro Mediano

    Neurosymbolic systems seek to combine the strengths of two major classes of AI algorithms: neural networks, able to recognise patterns in unstructured data, and logic-based systems, capable of powerful reasoning. One of the...

    Read more

  • Improving Robustness of Pre-Trained Language Models

    Project ID: STAI-CDT-2023-KCL-25
    Themes: Logic, Norms, Reasoning
    Supervisor: Yulan He

    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...

    Read more

  • Trusted Collective Intelligence through Norms, Ontologies and Provenance

    Project ID: STAI-CDT-2023-KCL-12
    Themes: AI Provenance, Norms
    Supervisor: Elena Simperl, Dr Timothy Neate

    Collective intelligence (CI) communities are among the greatest examples of collaboration, capability, and creativity of the digital age. CI communities allow large groups of individuals to work together towards a shared...

    Read more

  • Automatic Testing and Fixing Learning-based Conversational Agents with Knowledge Graphs

    Project ID: STAI-CDT-2023-KCL-10
    Themes: Norms, Verification
    Supervisor: Jie Zhang, Mohammad Mousavi

    Background: Learning-based conversational agents can generate conversations that violate basic logical rules and common sense, which can seriously affect user experience and lead to mistrust and frustration. To create...

    Read more

  • Data Bias Evaluation and Mitigation via Rule-based Classification

    Project ID: STAI-CDT-2023-KCL-9
    Themes: Norms
    Supervisor: Jie Zhang, Gunel Jahangirova

    Motivation: Training data can be severely biased. The existing metrics of data bias are based on data balance situations conditioned on protected attributes. This is coarse-grained and does not consider the relationship...

    Read more

  • Computational Social Choice and Machine Learning for Ethical Decision Making

    Project ID: STAI-CDT-2023-KCL-5
    Themes: AI Planning, Argumentation, Norms, Reasoning
    Supervisor: Maria Polukarov

    The problem of ethical decision making presents a grand challenge for modern AI research. Arguably, the main obstacle to automating ethical decisions is the lack of a formal specification of ground-truth ethical principles,...

    Read more

  • Causal Decentralised Finance

    Project ID: STAI-CDT-2022-KCL-3
    Themes: Logic, Norms, Verification
    Supervisor: Hana Chockler

    The goal of this project is to develop a causality-based framework for the analysis of decentralised finance (DeFi), based on the principled approach of actual causality [1] and responsibility [2], the latter pioneered by...

    Read more