Open Early Stage Researcher/PhD Position in Artificial Intelligence: Explaining Bayesian Networks

Open Early Stage Researcher/PhD Position at University of Aberdeen (UNIABDN), United Kingdom, for the NL4XAI project

Reference number: NL4XAI- ESR3

PhD research topic: Explaining Bayesian Networks

Objectives: To develop techniques for explaining Bayesian and probabilistic reasoning, especially Bayesian networks, to different types of users. Bayesian reasoning is transparent and sound, but very different from human reasoning, especially amongst people who are not domain experts. We will empirically explore the difficulties that different types of users have in understanding Bayesian networks; create an algorithm for generating appropriate explanations for different types of users; and empirically evaluate the effectiveness of this algorithm.

For more information, see http://ehudreiter.com/phd-explaining-bayesian-reasoning

Expected Results:

In-depth understanding of the state of the art in explaining Bayesian reasoning, especially in Bayesian networks.
Analysis of the difficulties different types of people have in understanding Bayesian reasoning.
Algorithm for generating appropriate explanations for different users of Bayesian reasoning.
Implementation of the algorithms, and integration into a standard tool for examining Bayesian networks.
Evaluation of the effectiveness of the algorithm in increasing user understanding, trust, and decision making.
Collaboration with and supporting other NL4XAI- ESRs working on related topics, including NL4XAI- ESR2, NL4XAI-ESR4, and NL4XAI-ESR10

Host institution: University of Aberdeen- UNIABDN (United Kingdom)

PhD Enrolment: University of Aberdeen- UNIABDN (United Kingdom)

Secondments: The ESR will undertake two secondments.

Supervisors:
Main Supervisor:
Prof. Ehud Reiter, Department of Computing Science – University of Aberdeen (UNIABDN), e.reiter en abdn.ac.uk
PhD Co-Supervisor:
Prof. Nir Oren, Department of Computing Science – University of Aberdeen (UNIABDN)
Dr. Nava Tintarev, Department of Data Science and Knowledge Engineering, University of Maastricht (UM)

General requirements:

Mobility: At the time of recruitment, the researcher must not have resided, or carried out his/her activity in United Kingdom for more than 12 months in the 3 years prior to recruitment date. Time spent as part of a procedure for obtaining refugee status under the Geneva Convention is not taken into account.
Career: When starting their contract (expected in April 2022), selected researchers should be within the first four years of his/her research careers and not have been awarded a doctoral degree prior to the application.
The candidate must be working exclusively for the action.
Visa: Any appointment will require confirmation of the right to work in the UK and ability to secure a valid visa, if required, from UK Visas and Immigration.

Specific requirements:

Degree: Good undergraduate or Masters degree in Computer Science or Artificial Intelligence, providing access to PhD program.
Language: Excellent command of English, together with good academic writing and presentation skills.

Desirable skills:

Background in NLP, NLG, argumentation, explainable AI, and/or probabilistic and Bayesian reasoning
Ability to work independently and as part of a team.
Strong motivation to pursue a PhD degree.
Strong interest in interdisciplinary scientific work

Estimated starting date: 1st April 2022

Contract: Full-time contract

Duration: for 18 months from the starting date, subject to approval of a project extension, including 2 secondments at other consortium members’ premises (see Secondment section)

Further information: After the contract and PhD fellowship ends, we may be able to provide a PhD studentship (at the standard UKRI stipend) for the remainder of the PhD, subject to availability of funding and to the fulfilment of objectives and quality of the results obtained by the PhD fellow.

Salary: £36096/year

Apply: https://nl4xai.eu/open_position/esr3-explaining-bayesian-networks/