Joseph Early – Medium

Joseph Early

Pinned

Joseph Early
in
Towards Data Science

How to create Latex tables directly from Python code

Copying tables of results from the console into a Latex report can be tedious and error fraught — so why not automate it?

3 min readJun 30, 2020

--

How to create Latex tables directly from Python code

--

Joseph Early
in
Level Up Coding

Mastering Subplot Legends in Matplotlib

A data visualisation tutorial on adding legends to Matplotlib figures involving subplots. Code and examples included!

4 min readMar 8, 2023

--

Mastering Subplot Legends in Matplotlib

--

Joseph Early

AI could help predict suicides — but rushing the technology could lead to big mistakes

AI has great potential to save the lives of mental health patients, but care must be taken to ensure it’s used safely and correctly.

5 min readOct 20, 2022

--

AI could help predict suicides — but rushing the technology could lead to big mistakes

--

Joseph Early
in
Towards Data Science

AI can produce prize-winning art, but it still can’t compete with human creativity

People consider creativity to be inherently human. However, AI has reached the stage the stage where it can be creative as well.

5 min readSep 30, 2022

--

1

AI can produce prize-winning art, but it still can’t compete with human creativity

--

1

Joseph Early
in
Towards Data Science

Explaining AI for High Resolution Images

AI can be used to make automated decisions based on high resolution images, but can we understand those decisions?

6 min readJun 14, 2022

--

A view of the Earth from space with a satellite looking towards the Earth’s surface.

--

Joseph Early
in
Towards Data Science

Mastering Inset Axes in Matplotlib

Inset axes are a fantastic (and often underutilised) tool in Matplotlib. Let’s see what they can do, and how to use them.

4 min readJun 8, 2022

--

Mastering Inset Axes in Matplotlib

--

Joseph Early
in
Towards Data Science

Understanding the Outputs of Multi-Layer Bi-Directional LSTMs

In this short tutorial, I breakdown the outputs of Multi-Layer Bi-Directional LSTMs, with an example of how to do so in PyTorch.

5 min readMar 5, 2022

--

2

Understanding the Outputs of Multi-Layer Bi-Directional LSTMs

--

2

Joseph Early
in
Predict

Can AI solve the world’s hardest Go problem?

Igo Hatsuyoron 120 is the hardest Go problem in the world. Let’s explore the most recent developments in applying AI to this problem.

8 min readFeb 12, 2022

--

Can AI solve the world’s hardest Go problem?

--

Joseph Early
in
Towards Data Science

The Potential of Gated Linear Networks for Online Learning

A recent publication from DeepMind brings an interesting new take on sample-efficient online learning.

6 min readJul 16, 2020

--

The Potential of Gated Linear Networks for Online Learning

--

Joseph Early
in
The Startup

What’s hot in Multi-Agent Systems?

Multi-Agent Systems research has been a long standing topic in AI, but what are AI researchers in the UK currently working on?

8 min readFeb 26, 2020

--

1

What’s hot in Multi-Agent Systems?

--

1

Joseph Early

Joseph Early

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

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams