Ferenc Huszár

For students

I am currently on sabbatical, and I haven't been able to respond to enquiries about future PhD and MPhil students, apologies.

I am planning to select students whose interests and expertise lines up with our current interests on the theory of deep learning: studying learning dynamics in neural networks, characterising and understanding generalisation and extrapolation phenomena in autoregressive language models, studying neural network behaviour in algorithmic/mathematical datasets.

Topics from my past I no longer work on: computer vision, superresolution or image compression, recommender systems, Bayesian/probabilistic graphical models.

I currently don't have a good way to host interns and visiting students in Cambridge.

About me

I'm Ferenc Huszár, Senior Lecturer in Machine Learning at the University of Cambridge. I recently joined the Department of Computer Science and Technology, a nice and cozy department, where we're building a new machine learning group with Neil Lawrence and Carl Henrik Ek and others. I'm interested in principled deep learning techniques: optimization, generalization, representation, transfer, meta-learning, and so on.

I did my PhD in Bayesian machine learning with Carl Rasmussen, Máté Lengyel and Zoubin Ghahramani over at the Engineering Department in Cambridge. I worked on topics of approximate inference [1, 2], active learning [3, 4], and applications of these to sciences [5, 6].

Following my PhD I worked in various jobs in the London tech/startup sector. My highlight as a researcher is joining Magic Pony Technology, a startup where we developed deep learning-based image superresolution [7, 8] and compression [9] techniques. After Twitter's acquisition Magic Pony, I have worked on a range of ML topics, like recommender systems [10, 11] and fair machine learning.


I started this blog some time ago but now it kind of has its own life. inFERENCe got started when, in 2015, I returned to machine learning research after a 3-year stint as a data scientist. I basically slept through the deep learning revolution. In those three years, many things happened, so I had to play catch up.

Initially, these blog posts helped me understand the body of literature I have missed: generative adversarial networks, variational autoencoders, representation learning, etc. Nowadays, I continue reading and writing about current papers, trying to reinterpret them and find connections to things I know, usually ending up with some kind of KL divergence.

If you're new here and want to get a taste, you may want to start with these crowd favourites:


You can send me an email to fh277@cam.ac.uk, follow me on twitter @fhuszar, or look at my Google scholar profile.