Henry Gouk
Lecturer In Machine Learning at The University of Edinburgh
City of Edinburgh, Scotland, United Kingdom
Summary
👤
Senior🎓
Top SchoolHenry Gouk is a Lecturer in Machine Learning at the University of Edinburgh and co-leads the Bayesian and Neural Systems group, bringing 13 years of experience in research-engineering roles across academia and industry. His work focuses on AI engineering—designing efficient, robust, and reliable ML methods that improve compute and data efficiency in real-world systems. He has a PhD in Machine Learning from the University of Waikato and a track record of practical contributions, from implementing AdaGrad for the MOA stream-mining framework to fixing critical memory and stability issues in a high-performance FFT library. Comfortable moving between theory, code, and systems, he blends mathematical rigor with low-level engineering (including RTL and high-throughput neuroscience model implementations). Based in Edinburgh, he combines academic leadership and active open-source involvement to push ML methods toward production-ready reliability.
13 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (PhD), Machine Learning, Doctor of Philosophy (PhD), Machine Learning at University of Waikato
Stackoverflow
36reputation
5kreached
1answer
0questions
Github Skills (14)
algorithm10
c1710
data-structures10
javas10
memory-management10
algorithms10
sgd10
machine-learning10
machine-learning-algorithms10
c1110
java10
data-structure10
performance-optimization9
weka6
Programming languages (8)
Github contributions (5)
Waikato/moa
Nov 2016 - Dec 2018
MOA is an open source framework for Big Data stream mining. It includes a collection of machine learning algorithms (classification, regression, clustering, outlier detection, concept drift detection and recommender systems) and tools for evaluation.
Role in this project:
ML Engineer
ML EngineerContributions:16 commits, 5 PRs, 11 comments in 2 years 1 month
Contributions summary:Henry implemented the AdaGrad optimization algorithm for use in online machine learning models within the MOA framework. The changes included the initial implementation, refactoring to subclass the SGD class, adding documentation, and fixing a derivative error. The user also addressed several potential bugs and improved code readability. This work demonstrates a focus on contributing to the core machine learning algorithms of the MOA project.
pythondata-streamstreamdriftclassification
anthonix/ffts
Jun 2013 - Nov 2013
The Fastest Fourier Transform in the South
Role in this project:Back-end Developer
Back-end DeveloperContributions:5 commits in 5 months
Contributions summary:Henry primarily focused on fixing memory leaks and other bugs in the `ffts_real_nd.c` file. Their work involved addressing issues related to multi-dimensional transforms and null pointer checks, improving the stability and correctness of the Fourier Transform implementation. The user also addressed a specific issue (#5 and #9) and made changes related to buffer sizes. Overall, the contributions concentrated on the core functionality and performance of the FFT library.
transformfastestsouthfourierfourier-transform
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.