Subject: Machine Learning

-This project is taken and no longer available Machine-learning based, data analysis of energy consumption of 5G Networks.

Marco Ruffini (email | all projects)

Project Description:  We are witnessing a new green transformation of communication networks, which is driven by the European green agenda. In terms of cellular networks, one of the driving forces enabling intelligent control is the O-RAN architecture (Open Radio Access Networks), which allows to dynamically optimize the network performance. O-RAN makes it possible to use … Read more

– This project is taken and no longer available – Development of digital twins of optical networks using machine learning

Marco Ruffini (email | all projects)

Project Description:  Over the past few years, telecommunications networks have migrated towards concepts of virtualisation and programmability, which has recently also affected the optical layer [1]. This has provided the opportunity to build more intelligent control of optical networks, for example to predict quality of transmission and thus improve overall network utilisation, as transmission channels … Read more

[Taken] Project Proposal: Machine Learning for Mobility Model Identification and Feature Understanding in Large Networking Datasets

Merim Dzaferagic (email | all projects)

In the era of large-scale communication networks, understanding user mobility patterns is crucial for optimizing network resources, improving service quality, and enhancing user experience. Mobility models provide insights into how users move within a network, influencing network planning, resource allocation, and handover decisions. However, traditional approaches to identifying these models often rely on predefined assumptions … Read more

Reconstructing Redacted Text Using A Tranformer LLM

Doug Leith (email | all projects)

Currently, the main method for enhancing the privacy of text is redaction i.e. masking out selected key words such as names, emails etc. While this is effective for removing obvious personally identifiable information, redacted text may potentially still leak textual patterns that can reveal authorship, sensitive topics (e.g. that the text relates to a medical … Read more

How Best To Optimise Machine Learning Hyperparameters?

Doug Leith (email | all projects)

When designing and training a neural network model the hyperparameters include the SGD step size, mini-batch size, gradient decay policy, choice of regularisation etc. Selecting values for these hyperparameters is a key step in obtaining a useful model. While selection is commonly based on heuristics and trial and error, there is also much interest in … Read more

Training A Transformer LLM To Play Tic Tac Toe

Doug Leith (email | all projects)

Transformer neural nets have transformed natural language processing, but they can also be applied to other sequences not just sequences of words. In particular, they can be applied to game playing, which consists of a sequence of moves and where the task is to predict a good next move. In this project you will investigate … Read more

Coastal Erosion Prediction Using Functional Data Regression

Mimi Zhang (email | all projects)

Coastal erosion, defined as the loss of coastal lands due to the net removal of material near the shoreline, poses significant hazards to people, infrastructure, the environment, and cultural heritage. The coast is a critical junction for environmental settings, human activities, infrastructure, and sensitive ecosystems, making coastal erosion a pressing concern. Ireland’s coastline features both … Read more

Personalised Federated Learning

Meriel Huggard (email | all projects)

Federated learning is used in distributed collaborative networks where multiple clients coordinate to train AI models without the need to share raw data. This is advantageous in a number of settings; for example; in health care where there are privacy/ethical issues associated with sharing data across multiple sites and in IoT networks where the sharing … Read more

Big-data in language brain science (taken)

Giovanni Di Liberto (email | all projects)

Auditory communication has a central role in our society. However, it remains unclear how our brains allow us to understand complex sounds, such as speech and music. The use of machine learning methods to study neural data has recently led to a major paradigm shift, greatly advancing our understanding of auditory perception. The Di Liberto … Read more