Henry Gouk

Henry Gouk is a Lecturer in Machine Learning at the School of Informatics, The University of Edinburgh. He is affiliated with the Institute for Adaptive and Neural Computation, where his research focuses on foundational aspects of machine learning and deep learning.

His research interests lie at the intersection of deep learning theory and practical model development. Key areas include self-supervised representation learning, transfer learning, model regularization techniques, and the theoretical enforcement of Lipschitz continuity in neural networks to improve stability and generalization. His work addresses core challenges in how models learn, adapt, and generalize across tasks.

The recent publications highlight a consistent focus on improving the reliability and transferability of deep learning models. Themes include evaluating few-shot learning methods, understanding self-supervised learning transfer, and developing regularization strategies that enhance fine-tuning and model robustness. These works are published in top venues such as CVPR, ICLR, and IEEE Signal Processing Magazine.

He supervises several PhD students, including Philipp Bomatter, Jack Geary, Cameron Barker, Taehoon Kim, and Fady Rezk, often in collaboration with Professor Timothy Hospedales. While no specific grants are mentioned, his active publication and software output suggest ongoing research funding and academic engagement.

Henry Gouk contributes to the research community through open-source software, notably the keras-lipschitz-networks repository on GitHub, which implements methods from his work on Lipschitz regularization. His research is conducted within the Institute for Adaptive and Neural Computation, a leading center for machine learning research at the University of Edinburgh.