School of Computer Science and Statistics
As a piece of language, a narrative may be regarded as a sequence S of sentences about a sequence E of events. The possibility that the order of E does not align with S (violating so-called iconicity of sequence) is one of many challenges in understanding narratives. Others include the variety of granularities and the … Read more
The aim of this project is to understand the interplay between randomness and optimization in the choice of a Markov decision process and of a policy, working with simple examples such as gridworlds. Particular attention will be paid to entropy (maximization and regularization).
Sports analytics increasingly relies on machine learning models to understand and predict player behavior, strategy, and outcomes. In team sports like rugby, pose estimation models can extract player keypoints (e.g., body joint locations) from match footage or sensor data, enabling automated performance analysis. However, despite recent progress in pose-based classification tasks (e.g., identifying tackles, passes, … Read more
Sign Language Recognition (SLR) is a field of Computational Linguistics that sits at the intersection of Computer Vision and Natural Language Processing – aiming to effectively extract salient linguistic features from visual data of sign language users. Recent SLR research has centered Machine Learning approaches, however, these methods typically rely on large-scale datasets which are … Read more
The Irish language is considered a low resource language as it has less data available for research, due to it being a minority language. This has implications on technological advancements in areas such as speech recognition, where limited data impacts the development of accurate and accessible digital tools. While transfer learning using multi-lingual models has … Read more
In many sports, coaches and athletes rely on annotated video footage to improve player performance, reduce the risk of injury, and analyse the game. This is also the case for rugby. Stakeholders at all levels, from amateur to professional, invest a lot of time and resources into annotating these games. With video quality and camera … Read more
The organization VoteWatch collected data for the European Parliament (EP) over the years 2014 – 2019. The data contain multiple information on the items being voted by the members of parliament (MPs) over that period, such as the area of a policy, the legal classification of the document being voted, etc. The aim of this … Read more
Due to the potential damage a cryptrographically relevant quantum computer could do to uses of widely used asymmetric cryptographic algorithms, a range of new “post-quantum” algorithms have been developed and are being widely deployed, e.g. in TLS in web browsers. This project is to investigate potential timing issues with implementations of such algorithms, likely reproducing … Read more
In this project we are exploring non-parametric methods for the estimation of probability density functions and for regression. The interested Student must be comfortable with Statistics and Mathematics. The Student must do a search about kernel density estimation and Nadaraya–Watson kernel regression. You may also have a look in Prof. Tsybakov’s book “Introduction to nonparametric … Read more
This project is particularly for the Students in Statistics and Sustainability. The interested Student should first check the papers: Establishing the link: Does web traffic from various marketing channels influence direct traffic source purchases? | Marketing Letters (springer.com) Unveiling digital dynamics: Do digital media investments impact organic branded searches? | Journal of Marketing Analytics The … Read more