Hi! I’m Paul. I am a Masters student in Informatics at the University of Edinburgh. I am interested in all things learning, of silicon and biological nature.

I have a strong background in deep learning and NLP, with my Bachelor’s thesis on compressing speech recognition models and my current Master’s thesis on distributed optimisation for deep neural networks.

For more details, see my previous work below.

When I’m not studying or researching deep learning methods, I am probably on a run🏃, taking photos📷 or hiking through the Scottish Highlands⛰️.

Research Interests

• Foundational Deep Learning Methods
  (Architectures, Training paradigms, Model compression, etc.)
• Natural Language Processing
• Computational Molecular Biology & Drug Discovery
• Computational Neuroscience: Biologically grounded models of cognition, behaviour and illnesses

Current research

• Distributed optimisation of Deep Neural Networks.
  Part of my Master’s thesis with Hao Tang.

• Leveraging Graph Neural Networks (GNNs) for the automated determination of parameter sets for 3D meshes, particularly for a novel spectral coarsening algorithm. This approach is aimed at expediting the computation of mesh parameters, to improve the efficiency of physics simulations on these meshes while maintaining a high level of accuracy. Previously, this task involved computationally expensive high-dimensional optimisation methods, which the GNN method significantly accelerates.
  Part of my research internship with Kartic Subr.

Previous work

1. Cross-Architecture Knowledge Distillation techniques for models with mismatched output dimensions.
   Bachelor’s Thesis, supervised by Hao Tang.
   Achieved an 80% (A2).
   View PDF →

2. Review of a Biologically Inspired Neural Network to Model PTSD and Eye Movement Desensitisation Reprocessing Therapy.
   Coursework in Computational Cognitive Neuroscience, taught by Peggy Seriès.
   Achieved an 80% (A2).
   View PDF →

3. Bioinformatics Analysis of Autism-Related Gene Networks.
   Coursework in Bioinformatics, taught by Ian Murray.
   Achieved a 79% (A3).
   View PDF →

Several other courseworks in Speech Processing, Computational Neuroscience, Machine Translation, etc. that achieved high marks of 80%+. While they’re not explicitly research-oriented, they have contributed significantly to my academic background and expertise in these domains.

Other experience

1. Teaching Assistant for Machine Learning @2023/24

2. Research Assistant intern for Kartic Subr, working on Graph Neural Networks for spectral coarsening of 3D meshes. @Summer 2023

3. Tutor for Machine Learning @2022/23

4. Exchange year at the University of Hong Kong @2021/2022

Favourite Courses

• Computational Neuroscience
• Natural Language Understanding, Generation, and Machine Translation
  (Yes, that’s all one course 😄)
• Automatic Speech Recognition
• Bioinformatics
• Quantum Information and Computation (Amazingly taught)

---