Computer Science Fully Funded PhD Scholarship: Elevating Comparative Judgement Using a Large-Scale Human-In-The-Loop Bayesian Active Learning Approach (Ecstatic)

3 Apr 2024
Job Information

Organisation/Company

Swansea University

Department

Central

Research Field

Computer science » Other

Researcher Profile

First Stage Researcher (R1)

Country

United Kingdom

Application Deadline

1 May 2024 - 23:59 (Europe/London)

Type of Contract

Other

Job Status

Full-time

Hours Per Week

35

Offer Starting Date

1 Oct 2024

Is the job funded through the EU Research Framework Programme?

Not funded by an EU programme

Is the Job related to staff position within a Research Infrastructure?

No

Offer Description

Computer Science: Fully Funded PhD Scholarship: Elevating Comparative Judgement Using a Large-Scale Human-In-The-Loop Bayesian Active Learning Approach (Ecstatic)

The Comparative Judgment (CJ) method, which has gained traction in UK schools over the past decade, involves assessors choosing the superior submission from a pair, rather than assigning a score to each one. This approach is less taxing for assessors and maintains accuracy for a small number of submissions. Recently, we developed a Bayesian active learning approach for CJ (BCJ; https://arxiv.org/abs/2308.13292 ), to solve a crucial problem of interaction-efficient pair selection while producing reliable estimations of ranks and predictive uncertainty.  

In this related project, for the first time, we will aim to scale BCJ to handle thousands of items (as opposed to tens of them), enabling ranking and scoring across schools and assignments. We will propose new methods to dynamically incorporate new items for ranking in BCJ in an interaction-efficient manner, and devise avenues for providing individual learners insight into their progress over time compared to their peers. We will evaluate these methods to establish their efficacy in helping assessors make informed decisions under uncertainty arising from the practical paucity of data and interactions, as well as better informing learners. These methods will be designed in collaboration with assessors and learners to ensure that they remain relevant and useful beyond the project completion. 

Requirements

Research Field

Computer science » Other

Education Level

Bachelor Degree or equivalent

Skills/Qualifications

Candidates must hold an Upper Second Class (2.1) honours degree or an appropriate master’s degree with a minimum overall grade at ‘Merit’ in Computer Science, Mathematics or a closely related discipline. If you are eligible to apply for the scholarship (i.e. a student who is eligible to pay the UK rate of tuition fees) but do not hold a UK degree, you can check our comparison entry requirements. Please note that you may need to provide evidence of your English Language proficiency. 

Specific Requirements

English Language: IELTS 6.5 Overall (with no individual component below 6.0) or Swansea University recognised equivalent. 

Desirable skills and attributes: 

• Excellent numerical and progamming skills;
• Knowledge of Python.; 
• Knowledge of Bayesian statistics, machine learning, and optimisation, or a willingness to learn.

This scholarship is open to candidates of any nationality.

Additional Information
Benefits

This scholarship covers the full cost of tuition fees and an annual stipend at £19,237.

Additional research expenses will also be available.

Eligibility criteria

Candidates must hold an Upper Second Class (2.1) honours degree or an appropriate master’s degree with a minimum overall grade at ‘Merit’ in Computer Science, Mathematics or a closely related discipline. If you are eligible to apply for the scholarship (i.e. a student who is eligible to pay the UK rate of tuition fees) but do not hold a UK degree, you can check our comparison entry requirements. Please note that you may need to provide evidence of your English Language proficiency. 

English Language: IELTS 6.5 Overall (with no individual component below 6.0) or Swansea University recognised equivalent. 

Desirable skills and attributes: 

• Excellent numerical and progamming skills;
• Knowledge of Python.; 
• Knowledge of Bayesian statistics, machine learning, and optimisation, or a willingness to learn.

This scholarship is open to candidates of any nationality.

 

Selection process

Please see our website for more information.

Website for additional job details

https://www.swansea.ac.uk/postgraduate/scholarships/research/computer-science-s…

Work Location(s)

Number of offers available

1

Company/Institute

Swansea University

Country

United Kingdom

City

Swansea

Postal Code

SA2 8PP

Geofield

Where to apply

Website

https://www.swansea.ac.uk/postgraduate/scholarships/research/computer-science-s…

Contact

City

Swansea

Website

https://www.swansea.ac.uk/postgraduate/scholarships/research/computer-science-su-nmm-phd-elevating-2024-rs590.php?utm_source=euraxess&utm_medium=scholarship&utm_campaign=postgraduate24&utm_content=pgr

Street

Singleton Park

Postal Code

SA28PP

E-Mail

[email protected]

STATUS: EXPIRED