The gates are open, come on in. (Photo by Ágatha Depiné on Unsplash)

Two of the biggest drawbacks for modern deep learning systems are how data hungry they are and how long they take to train (I’m looking at you GPT-3). These systems have access to all their data at the time of training, and revisit each piece of data multiple times over…

Making tables should be simple and elegant (Photo by Roman Bozhko on Unsplash).

Creating tables of results plays a major part in communicating the outcomes of experiments in data science. Various solutions exist for producing tables in Python and drawing them in the console output, but how do you transfer them to a written report? …

Can we get agents to cooperate and coordinate in teams? (Photo by Eric Krull on Unsplash)

Multi-agent systems (MAS) research has been a long standing topic in AI that has received a large amount of attention. I was recently fortunate enough to attend the UK-MAS Symposium at the Alan Turing Institute. The aim of the symposium was to bring together researchers from UK universities and practitioners…

Finally, robotic beings rule the world — pictures of the Terminator and HAL are just played out at this point. (Flight of The Conchords, Robots)

The past decade has seen many interesting and impressive developments in tech (but it hasn’t been without its fair share of flops either). AI research and development have seen a huge increase in the past ten years, due in part to the accessibility of large datasets and greater compute power…

Reproducibility means hitting the right target, every time (Photo by Oliver Buchmann on Unsplash)

With the emerging reproducibility crisis in data science, it is becoming more important for data science researchers to provide open access to their code. An essential element of this is ensuring continual performance of existing experiments as code changes. …

A single neural network is able to perform multiple reinforcement learning tasks.

This article summaries some of the research I did as part of my undergraduate degree at the University of Southampton. I developed a novel technique for reducing ‘catastrophic forgetting’ — the pitfall that machine learning systems encounter when trying to learn several task sequentially. However, instead of focusing on learning…

Joseph Early

PhD student at the Alan Turing Institute and the University of Southampton. Machine Learning and Explainable AI www.jearly.co.uk

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store