I am a Senior Research Scientist in the Google Brain team, Zurich. I completed my PhD in the Cambridge CBL lab, with Zoubin Ghahramani, and Máté Lengyel. I work on Machine Learning, and I am particularly interested in transfer learning, representation learning, AutoML, generative models, and natural language processing.
Publications
Parameter-Efficient Transfer Learning for NLP
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly ICML 2019
[paper]
Self-Supervised GANs via Auxiliary Rotation Loss
Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby CVPR 2019
On Self Modulation for Generative Adversarial Networks
Ting Chen, Mario Lucic, Neil Houlsby, Sylvain Gelly ICLR 2019
Transfer Learning with Neural AutoML
Catherine Wong, Neil Houlsby, Yifeng Lu, Andrea Gesmundo NeurIPS 2018
[paper]
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang ICLR 2018
[paper]
Efficient Bayesian Active Learning and Matrix Modelling
Neil Houlsby PhD Thesis 2014
[pdf]
A Filtering Approach to Stochastic Variational Inference
Neil Houlsby, David Blei NIPS 2014
[paper]
Cold-start Active Learning with Robust Ordinal Matrix Factorization
Neil Houlsby, José Miguel Hernández-Lobato, Zoubin Ghahramani ICML 2014
[paper] [supplementary] [video] [code]
Stochastic Inference for Scalable Probabilistic Modeling of Binary Matrices
José Miguel Hernández-Lobato, Neil Houlsby, Zoubin Ghahramani ICML 2014
[paper] [supplementary] [video] [code]
Probabilistic Matrix Factorization with Non-random Missing Data
José Miguel Hernández-Lobato, Neil Houlsby, Zoubin Ghahramani ICML 2014
[paper] [supplementary] [video] [code]
A Scalable Gibbs Sampler for Probabilistic Entity Linking
Neil Houlsby, Massimiliano Ciaramita ECIR 2014
[paper]
Active learning for Interactive Visualization
Tomoharu Iwata, Neil Houlsby, Zoubin Ghahramani AISTATS 2013
[paper]
Cognitive Tomography Reveals Complex Task-Independent Mental Representations
Neil Houlsby, Ferenc Huszár, Mohammad Ghassemi, Gergő Orbán, Daniel Wolpert, Máté Lengyel Current Biology 2013
[paper]
Experimental Adaptive Bayesian tomography
Konstantin Kravtsov, Stanislav Straupe, Igor Radchenko, Gleb Struchalin, Neil Houlsby, Sergey Kulik Physical Review A 2013
[paper]
Statistical Fitting of Undrained Strength Data
Neil Houlsby, Guy Houlsby Géotechnique 2013
[paper]
Adaptive Bayesian Quantum Tomography
Ferenc Huszár, Neil Houlsby Physical Review A 2012
[paper]
Collaborative Gaussian Processes for Preference Learning
Neil Houlsby, Ferenc Huszár, Jose M. Hernández-lobato, Zoubin Ghahramani NIPS 2012
[paper]
Bayesian Active Learning for Gaussian Process Classification
Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, Máté Lengyel
NIPS Workshop on Bayesian optimization, experimental design and bandits: Theory and applications 2011
[paper]