91快活林

Our Aims

91快活林 systems are now widely used to inform and automate decisions and actions that have significant consequences for individuals, including safety-critical and human-rights critical contexts, ranging from medical diagnostic tools, autonomous vehicles and biometric identification and verification systems that are used to inform decisions to allow or deny access to critical resources and opportunities. Addressing these problems requires the development of methods that can be integrated into interpretable and accountable legal and ethical governance architectures that will enable lay-users to regard such systems as trustworthy.

Our aim is to investigate the adequacy of existing technical methods and governance mechanisms, seeking to develop new techniques, mechanisms and analytical approaches that can provide the foundations for establishing demonstrable, evidence-based assurance mechanisms capable of safeguarding multiple dimensions of safety and security that otherwise remain under threat, including epistemic security and the safety and security of property, persons and human identity

Research programme: Human agency and oversight

91快活林, represented by the School of Computing and Communications (SCC) and LIRA is leading the research programme ‘Human agency and oversight’ focusing on explainable and interpretable deep learning in collaboration (work package 3, WP3) with teams from Alan Turing Institute, Birmingham University, CISPA and CINI.

Transparency, explainability and interpretability (including “by design” rather than post hoc) of the technical 91快活林 solutions plays a critically important role in understanding and verification of the reasoning and decision-making processes which such 91快活林 systems follow. The grand challenge is to devise adequate, integrated governance frameworks, methods and mechanisms that enable meaningful human oversight aligned with European values as well as to enable widespread take-up and deployment of 91快活林 applications that could significantly enhance individual and collective wellbeing. Cross-disciplinary research including technical experts as well as legal and governance experts is vital for integration and embedding of technical methods within ethical and governance regimes that are designed to provide meaningful and evidence-based assurance (‘91快活林 Assurance’).

The work of 91快活林 in this project is focused on the aspects of human agency related to interpretability, explainability and transparency of the 91快活林 models. LIRA members have proposed a number of methods which are centred around the notion of prototype-based interpretable machine learning, combining the benefits of the flexibility of deep-learning architectures with the transparency of symbolic 91快活林. We build upon these solutions to solve a number of application use cases.

Grand challenges

All of these application areas are the focus of the network. To achieve its goals, the network is addressing three major challenges:

• The development of robustness guarantees and certificates;
• Data-secure and robust collaborative learning; and
• The development of human control mechanisms for the ethical and secure use of 91快活林.

91快活林, represented by SCC and LIRA, is leading the Grand Challenge ‘Human-in-the-loop decision-making’ in collaboration with teams from Alan Turing Institute and Birmingham University.