PhD Student
University of Edinburgh

Hey, I'm Ben.

Research

Here's some information about the work I do, that I find particularly interesting.
Send me a message if we have overlapping interests.
🎞️ Memory & Planning
How do we even use memory to plan ahead? We don’t consciously think through every past experience; instead, we pull up what we need on the fly, and use it to plan our next steps. In deep learning, though, using memory to drive planning is tricky. Models can recall specific steps, but they struggle to bring up the right info at the right time and adapt it to new situations. So, how can we design representations that allow models to dynamically use relevant past experiences to guide planning for solutions?

Memory and Planning in Brains and Machines - a very interesting perspective.
Geometry of neural computation unifies working memory and planning - a unification of planning and memory.
Survey on Memory-Augmented Neural Networks - a survey of memory models in NNs.
Imagination, Planning, and Working Memory - not AI related per-se, but imagination is a holy grail of planning.
🧠 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?

Representation Learning Review - old but gold.
I-JEPA - Yann really seems to love these JEPA architectures.
Multimodal Representation Learning - what it says on the tin.
🔄 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 Dartmouth Proposal - such a cool read.
Path to AMI - Yann LeCun's take.
On the Measure of Intelligence - François Chollet's take.
The Alberta Plan - Richard Sutton's take.

experience