Posts by Collection

projects

AstronomicAL: an interactive dashboard for visualisation, integration and classification of data with Active Learning

Presented at Journal for Open Source Software, 2021

AstronomicAL is a human-in-the-loop interactive labelling and training dashboard that allows users to create reliable datasets and robust classifiers using active learning. This technique prioritises data that offer high information gain, leading to improved performance using substantially less data. The system allows users to visualise and integrate data from different sources and deal with incorrect or missing labels and imbalanced class sizes. We illustrate using the system with an astronomical dataset due to the field’s immediate need; however, AstronomicAL has been designed for datasets from any discipline.
Read more

P.I.E.S: Passive Information Extraction System

Published:

The Passive Information Extraction System (P.I.E.S) analyses a live transcript of the conversation to improve customer experience by allowing service desk operators to concentrate on the human interaction rather than data collection. The system processes all information from the conversation in real time and enters it on the system while the call operator concentrates on the customer’s welfare. The system uses a BERT model trained on the Stanford Question Answering Dataset (SQuAD). One of the main advantages of the implemented system is the ability to produce more training data with every call the company handles.
Read more

Rave Cave

Published:

For a 3rd Year group project, we created Rave Cave, a multiplayer rhythm-based dungeon crawler where large amounts of players rock out simultaneously in time to the music. Players must cooperate with their team to solve puzzles and complete complex button sequences - all in time to the beat of the music. We created our own game engine in C++ by integrating our custom code with external libraries.
Read more

publications

talks

Presentation on MLOps and Kubeflow

Presented at University of Bristol, 2020

Lecture on MLOps and Kubeflow presented to 1st Year Interactive AI CDT students on Interactive AI Team Project unit. This talk aims to give a very accessible introduction to the need for MLOps by linking to the similarities of the development of DevOps systems. By looking into the effect of increasing scale (team size, customer base or project size), students will see potential problems with how their current development practices may not be sustainable when applied to ML projects at an industry-scale. Finally, there is a brief overview of Kubeflow and its main components, showing why they are useful and how they can potentially solve the previous issues. Read more

Computer Science, AI & Me

Presented at Insight into University - Engineering Development Trust, 2021

Webinar presented to over 100 sixth form students. The presentation began with telling the students about my academic life and how I went from a widening participation background to studying for a PhD at Bristol. This led to an introduction to what Computer Science is (and is not) like at university. The final part gave the students the (very brief) foundations of what Machine Learning and AI really are. Unfortunately, the adoption of these tools has led to a large amount of over-exaggeration and overuse of certain buzzwords throughout the industry, making it seem like companies are doing super complicated and ground-breaking things when most of the time they’re doing nothing more than the Maths the students use in their A-Level studies. Read more

AI & ML: Cutting Through The Hype

Presented at Sutton Trust Summer School, 2021

Webinar presented to 60 sixth form students who intend to study Engineering at university. The presentation starts with an introduction to what Computer Science is (and is not) like at university. Following this, the (very brief) foundations of what Machine Learning and AI really are. Unfortunately, the adoption of these tools has led to a large amount of over-exaggeration and overuse of certain buzzwords throughout the industry, making it seem like companies are doing super complicated and ground-breaking things when most of the time they’re doing nothing more than the Maths the students use in their A-Level studies. I also show the Dot-Com Boom and the AI Winter as examples for how overhyping can be damaging for research progress and the economy. Read more

The Hidden Difficulties of Machine Learning

Presented at Access To Bristol, 2021

On-campus presentation to 30 local sixth form students who intend to study Engineering at university. This presentation immediately followed the AI & ML:Cutting Through The Hype talk and was used to show how ML tasks are often not as straightforward as they may seem. This talk is very interactive with the aim that the students are able to discover the problems that appear themselves and see why certain solutions may not be sufficient for a problem. Read more

teaching