Marc Deisenroth
DeepMind Chair of Machine Learning and Artificial Intelligence
University College London
Interests
- Machine learning
- Gaussian processes
- Reinforcement learning
- Robotics
- Meta learning
Latest
- Dr. Rosca
- Student Projects 2022
- Dr. Wilson
- Dan Roy: Admissibility is Bayes Optimality with Infinitesimals
- Benjamin Chamberlain: A Continuous Perspective on Graph Neural Networks
- Dr. Petangoda
- Paper accepted at TMLR
- Michalis Titsias: Functional Regularisation for Continual Learning with Gaussian Processes
- Paper accepted at TMLR
- Paper accepted at JMLR
- Shahine Bouabid and Siu Chau: Deconditional Downscaling with Gaussian Processes
- SML@NeurIPS 2021
- Dr. Terenin
- Dr. Sæmundsson
- Geoff Pleiss: Understanding Neural Networks through Gaussian Processes, and Vice Versa
- Three papers accepted at ICML 2021
- Papers accepted at AIES 2021
- Best Student Paper Award at AISTATS 2021
- Fariba Yousefi: Multi-task Learning for Aggregated Data using Gaussian Processes
- Ruha Benjamin: Reimagining the Default Settings of Technology & Society
- César Lincoln C. Mattos: Probabilistic ML-Applications and Modeling Investigations
- Dr. Kamthe
- Jackie Kay: Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities
- Dr. Moriconi
- Workshop on Bridging the Gap between Data-driven and Analytical Physics-based Grasping and Manipulation accepted at ICRA 2021
- Dhruva Tirumala: Using behavior priors for data efficiency in Reinforcement Learning
- Four Papers Acccepted at AISTATS 2021 and ICLR 2021
- Ti John: Gaussian processes for fun and profit: Probabilistic machine learning in industry
- SML@NeurIPS 2020
- Welcome Dr. So Takao
- Welcome, Jackie Kay
- Welcome, Sicelukwanda Zwane
- Welcome, Yicheng Luo
- Two Papers Acccepted at NeurIPS 2020
- Matérn Gaussian Processes on Riemannian Manifolds
- Probabilistic Active Meta-Learning
- MSc Project Submissions
- Chidubem Iddianozie: On the Prospects and Challenges of Machine Learning for Street Networks
- Tim G. J. Rudner: Inter-domain Deep Gaussian Processes
- Paper accepted at Machine Learning Journal
- High-Dimensional Bayesian Optimization with Manifold Gaussian Processes
- A Foliated View of Transfer Learning
- Cynthia Matuszek: Robots, Language, and Environments: Modeling Linguistic Human-Robot Interactions
- Estimating Barycenters of Measures in High Dimensions
- Honorable Mention Award for Outstanding Paper at ICML 2020
- Efficiently Sampling Functions from Gaussian Process Posteriors
- Healing Products of Gaussian Process Experts
- Stochastic Differential Equations with Variational Wishart Diffusions
- Christopher Jackson: 3D Seismic Reflection Data: Has the Geological Hubble Retained Its Focus?
- Aligning Time Series on Incomparable Spaces
- Variational Integrator Networks for Physically Structured Embeddings
- Three papers accepted at ICML 2020
- Mathematics for Machine Learning
- Dr. Olofsson
- Joanna Slawinska: Data-driven spectral analysis and nonparameteric predictions of climate dynamics
- Laura Mansfield: Can we use machine learning to predict global patterns of climate change?
- So Takao: Stochastic Advection by Lie Transport: A geometric framework for data-driven turbulence closure
- Yasemin Bekiroglu: Towards Robust and Goal-oriented Robotic Grasping and Manipulation
- Keshi He: Toward AI-powered Robots Served for IndustrialProductions and Healthcare
- Vincent Adam: Variational inference for Gaussian Process models: multi-GP regression and time-series models
- Rituraj Kaushik: Data-efficient adaptation in robotics using priors from the simulator
- Rika Antonova: Adaptive Kernels and Priors for Data-efficient Bayesian Optimization
- High-Dimensional Bayesian Optimization with Projections using Quantile Gaussian Processes
- Two papers accepted at AISTATS 2020
- Variational Integrator Networks
- Research Fellow/Senior Research Fellow position in Machine Learning for Climate Science
- Research Fellow/Senior Research Fellow position in Machine Learning for Robotics
- Vincent Adam: Doubly Sparse Variational Gaussian Processes
- Welcome to the team, Rasmus
- Dr. Salimbeni
- Samuel Kaski: Probabilistic Modelling with Experts
- Welcome to the team, Samuel
- Four papers accepted at NeurISP workshops
- Christian Walder: New Tricks for Estimating Gradients of Expectations
- Emtiyaz Khan: Learning-Algorithms from Bayesian Principle
- Paper on fast submodular function minimization accepted at NeurIPS 2019
- Sesh Kumar awarded DSI Fellowship
- Paper on deep GPs with importance-weighted variational inference accepted at ICML 2019
- JP Morgan Fellowship Award to Sanket Kamthe
- GPdoemd: A Python Package for Design of Experiments for Model Discrimination
- Three papers accepted at NeurIPS 2018
- Meta Reinforcement Learning with Latent Variable Gaussian Processes
- Dr. Chamberlain
- Meta-learning paper accepted at UAI 2018
- Marc Deisenroth receives Early Career Award
- Paper on Real-Time Community Detection accepted at PLOS ONE
- Probabilistic Model-based Imitation Learning