PhD Student
University of Edinburgh

Research

Here's some information about the work I do, that I find particularly interesting.
Send me a message if we have overlapping interests.

🔄 Continual Learning
Is there a myth of the objective? Does it even exist, or are we just chasing shadows? This leads onto the real question: how do we design an algorithm that will last for the next thousand years?

Continual Learning Survey
Another Continual Learning Survey - Both of these surveys are great
A Definition of Continual Learning - a definition of continual DRL by one of my PhD supervisors.

📜 Magnus Finis 
Stop doing research for the sake of research. What was the end goal again? How do we get there? Well, here are a few interesting takes.

Can Machines Think? - the man himself.
The Alberta Plan - Richard Sutton's take.
Path to AMI - Yann LeCun's take.
The Big World Hypothesis - short but sweet.

🎯 Zero-Shot Generalisation
Show a monkey how to stack some bricks, and it’ll ace the job no matter the shape, color, or pose. Teach the same trick to a DL model, and watch it have an aneurism when the colour of the brick changes. Personally, I'm not a fan of drowning models in heaps of training data, so how do we craft domain-invariant policies?

Zero-shot Generalisation in DRL Survey - really nice survey on this topic by the lot in DARK labs, UCL.
Open-Ended Learning - Even if you don't want to read this, at least get lost in its figures 🤤.
Domain Generalisation Survey - a broader look at the problem of domain invariance.
Generalisation in Cooperative MARL - an interesting look into combinatorial generalisation.

🧠 Representation Learning
When you learn something new, what does it even mean to understand it? It's something we do quasi-proactively; half the time, it's like a mental magic trick we perform almost on autopilot. This notion of learning in DL is usually achieved with representation learning, where a model learns representations from raw data. This currently works pretty dang well in single-domain supervised learning tasks, but how can we create representations that are more representative of the mess of a world we live in?

I-JEPA - can you even talk about representation learning without mentioning Yann's work?
V-JEPA - V0.2 of Yann's vision.
Representation Learning Review - old but gold.
Multimodal Representation Learning - what it says on the tin.

experience

A summary of my experience so far, spanning from my undergraduate days to my current PhD research.

• 
  PhD @ UoE
  Autumn '24 - Present
  
  

  Supervised by Amos Storkey and David Abel. My PhD research focuses on continual learning, generative modelling and generalisation to OOD tasks. I spend a lot of time tackling the learning plasticity-memory stability dilemma, however, I also like to dabble in zero-shot generalisation, representation learning, and Bayesian statistical modelling.

• 
  Senior Research Assistant
  Spring - Summer '24
  
  

  Worked on a research project for an industry client, supervised by Jonathon Hare and funded by Innovate UK. Built a system that localised and mapped objects within 3D point clouds of large vehicles.

• 
  Data Science Intern
  Autumn '23
  
  

  Landed a Data Science internship at Cirium after a successful AI hackathon. Spent my time working on time-series forecasting and geospatial analysis using spatiotemporal DL techniques. Had a lot of fun with graph neural networks too.

• 
  Undergraduate Research Scholar
  Summer - Autumn '22
  
  

  Bagged a scholarship to spend the summer on a research project of my choosing. I spent my time exploring efficient ML techniques, especially digging into adaptive computation tricks like A-VIT.

• 
  Master's @ UoS
  Autumn '19 - Summer '23
  
  

  Spent 4 years doing my integrated Master's in Electronic Engineering with Artificial Intelligence at the University of Southampton. I was lucky enough to be supervised by some great people, including Jonathon Hare (Master's thesis), Geoff Merrett (3rd year thesis), and Lei Xun (3rd year thesis).