Fully Funded Doctoral Studentship in conjunction with the FUN2MODEL project

Supervisor: Professor Marta Kwiatkowska

Start Date: October 2020

The Department of Computer Science at the University of Oxford is currently looking for outstanding candidates to fill one doctoral studentship position available from January 2020 or as soon as possible thereafter on the five-year ERC Advanced Grant FUN2MODEL “From FUNction-based TO MOdel-based automated probabilistic reasoning for DEep Learning” (fun2model.org) led by Professor Marta Kwiatkowska, with Dr Dave Parker as an external collaborator. The project also funds an additional studentship and three postdoctoral positions, some of which have already been filled.

The FUN2MODEL project aims to make advances towards provably robust 'strong' Artificial Intelligence. In contrast to 'narrow' AI perception tasks realised by deep learning, which are limited to learning data associations, and sometimes referred to as function-based, 'strong' AI aims to match human intelligence and requires model-based reasoning about causality and 'what if' scenarios, incorporation of cognitive aspects such as beliefs and goals, and probabilistic reasoning frameworks that combine logic with statistical machine learning.

The objectives of FUN2MODEL are to develop novel probabilistic verification and synthesis techniques to guarantee safety, robustness and fairness for complex decisions based on machine learning; formulate a comprehensive, compositional game-based modelling framework for reasoning about systems of autonomous agents and their interactions, capturing data inference, cognitive reasoning and affective aspects; and evaluate the techniques on a variety of case studies with the goal to ensure provably robust and beneficial multi-agent collaborations.

ERC (European Research Council) Advanced Grants provide long-term funding for exceptional leaders to pursue ground-breaking, high-risk projects, that have the potential to make a difference in people’s everyday life and deliver solutions to some of our most urgent challenges.

This Studentship Project Description: The topic of this studentship is Fairness and bias in multi-agent interactions

Fairness and bias of algorithmic decisions is critical to ensure their acceptance in society, but has been lacking in recently deployed AI software, for example Microsoft’s bot Tay. As a result, a variety of definitions of algorithmic fairness and corresponding verification approaches have been developed. However, these do not capture the influence of the cognitive and affective aspects of complex decisions made by autonomous agents, such as preferences and emotional state, which are essential to achieve effective collaboration of human and artificial agents. This project aims to develop a probabilistic, Bayesian framework based on cognitive modelling, probabilistic programming and causal inference for reasoning about fairness and bias in multi-agent collaborations, together with demonstrator case studies and associated software tools.

The successful applicant will have the opportunity to collaborate with other members of the FUN2MODEL project, and to utilise the methods, models and software, including PRISM model checker components, developed as part of the project towards own research objectives.

The post holder will be a member of Professor Marta Kwiatkowska’s research group with responsibility for: carrying out research as outlined above; collaborating with Professor Kwiatkowska and other members of the team; and assisting with project reporting, as required. The post holder will also have an opportunity to engage in teaching, and to provide guidance to junior members of the research group, including PhD and MSc students.

The post holder will join an internationally leading research group of Professor Marta Kwiatkowska, who has an extensive track record in probabilistic verification and pioneering research on safety verification for neural networks and trust in human-robot collaborations. The group has presented their work at leading conferences in concurrency, verification, AI, and robotics (notably CAV, CONCUR, TACAS, IJCAI, AAAI and ICRA), with Professor Kwiatkowska receiving multiple keynote invitations. More information about Professor Kwiatkowska’s research and PRISM model checker can be found here:

http://www.cs.ox.ac.uk/marta.kwiatkowska/  

https://royalsociety.org/science-events-and-lectures/2018/11/milner-lecture/

https://www.prismmodelchecker.org/

The project will provide an annual stipend to the student of at least £15600 per annum for 3.5 years. The project will also cover the cost of course fees at home/EU level (international students will need additional funding), travel to conferences and workshops, and provision for a laptop computer.

Applicants must satisfy the usual requirements for studying for a doctorate at Oxford. Candidates must also have good writing, communication and presentation skills (see the University's web pages on the DPhil in Computer Science for details).

You should apply online by 12 noon on Friday 10^th January 2020, quoting studentship reference CS-MK-2020

We expect to invite shortlisted applicants to interview on Monday 3^rd February 2020.

For further information about the project or for informal discussions about suitability, please contact Marta Kwiatkowska (marta.kwiatkowska@cs.ox.ac.uk ).  For further information about the studentship or the application process please e-mail Computer Science Graduate Admissions