Statistical Machine Learning Group
Statistical Machine Learning Group
Home
Team
Publications
Blog
Teaching
Talks
News
Openings
Reading
Recent & Upcoming Talks
2021
Fariba Yousefi: Multi-task Learning for Aggregated Data using Gaussian Processes
Aggregated data is commonplace in areas such as epidemiology and demography. For example, census data for a population is usually given …
March 25, 2021 16:00 — 17:00
online
Marc Deisenroth
Ruha Benjamin: Reimagining the Default Settings of Technology & Society
From everyday apps to complex algorithms, technology has the potential to hide, speed, and deepen discrimination, while appearing …
March 19, 2021 14:45 — 16:00
online
Marc Deisenroth
César Lincoln C. Mattos: Probabilistic ML-Applications and Modeling Investigations
Probabilistic modeling is a core component of modern machine learning. Nevertheless, at least from our local perspective, educational …
March 4, 2021 16:00 — 17:00
online
Marc Deisenroth
Slides
Jackie Kay: Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities
Recent advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore the concerns of the …
February 25, 2021 18:00 — 19:00
online
Marc Deisenroth
Slides
Video
Dhruva Tirumala: Using behavior priors for data efficiency in Reinforcement Learning
While reinforcement learning has shown great promise as a viable solution to many problems such as Go and Atari, it’s application …
February 11, 2021 16:00 — 17:00
online
Marc Deisenroth
Slides
2020
Ti John: Gaussian processes for fun and profit: Probabilistic machine learning in industry
When companies, whether start-ups or big corporations, talk about machine learning they usually mean some kind of neural network model. …
November 4, 2020 14:00 — 15:00
online
Marc Deisenroth
Thu Nguyen Phuoc: Neural rendering and inverse rendering using physical inductive biases
Computer graphics focuses on rendering high-quality 2D images from 3D scenes, with most research focusing on simulating elements of the …
October 4, 2020 14:00 — October 7, 2020 15:00
online
Alexander Terenin
Chidubem Iddianozie: On the Prospects and Challenges of Machine Learning for Street Networks
Our streets shape us in more ways than we can imagine. In this talk, I offer a unique view into the promising applications of machine …
September 23, 2020 11:00 — 12:00
online
Marc Deisenroth
Tim G. J. Rudner: Inter-domain Deep Gaussian Processes
Inter-domain Gaussian processes (GPs) allow for high flexibility and low computational cost when performing approximate inference in GP …
August 13, 2020 16:00 — 17:00
online
Marc Deisenroth
Slides
Cynthia Matuszek: Robots, Language, and Environments: Modeling Linguistic Human-Robot Interactions
As robots move from labs and factories into human-centric spaces, it becomes progressively harder to predetermine the environments, …
July 29, 2020 14:00 — 15:00
online
Marc Deisenroth
Christopher Jackson: 3D Seismic Reflection Data: Has the Geological Hubble Retained Its Focus?
In their seminal paper in 2002, Joe Cartwright and Mads Huuse referred to 3D seismic reflection data as the ‘Geological Hubble’, …
June 24, 2020 14:00 — 15:00
online
Marc Deisenroth
Video
Yasemin Bekiroglu: Learning and multi-modal sensing for robotic grasping and manipulation
Robots are envisioned as capable machines who easily navigate and interact in a world built for humans. However, looking around us we …
March 10, 2020 10:00 — 11:00
AI Centre, UCL
James Wilson
Joanna Slawinska: Data-driven spectral analysis and nonparameteric predictions of climate dynamics
The Earth’s system dynamics has an intrinsically multi-scale and nonlinear nature, which fundamentally affects the ability to …
March 2, 2020 13:30 — 14:00
AI Centre, UCL
Marc Deisenroth
Laura Mansfield: Can we use machine learning to predict global patterns of climate change?
To achieve long-term climate change goals, such as limiting global warming to 1.5 or 2°C, there must be a global effort to decide and …
March 2, 2020 11:00 — 11:30
AI Centre, UCL
Marc Deisenroth
So Takao: Stochastic Advection by Lie Transport: A geometric framework for data-driven turbulence closure
Way too often, observations from weather stations fall outside of the ensemble generated by initial uncertainty in weather models. This …
March 2, 2020 09:30 — 10:00
AI Centre, UCL
Marc Deisenroth
Yasemin Bekiroglu: Towards Robust and Goal-oriented Robotic Grasping and Manipulation
Robots are envisioned as capable machines who easily navigate and interact in a world built for humans. However, looking around us we …
February 27, 2020 15:30 — 16:00
AI Centre, UCL
Marc Deisenroth
Keshi He: Toward AI-powered Robots Served for IndustrialProductions and Healthcare
Recent advancement of AI technologies like deep learning or deep reinforcement learning greatly enhance robot’s …
February 27, 2020 14:00 — 14:30
AI Centre, UCL
Marc Deisenroth
Vincent Adam: Variational inference for Gaussian Process models: multi-GP regression and time-series models
Variational inference (VI) is a versatile framework to perform approximate inference in probabilistic models. Recent progress made it …
February 27, 2020 11:30 — 12:00
AI Centre, UCL
Marc Deisenroth
Rituraj Kaushik: Data-efficient adaptation in robotics using priors from the simulator
In the real world, a robot might face any unanticipated situation, such as damaged motors, unseen terrain conditions, faults in the …
February 27, 2020 10:00 — 10:30
AI Centre, UCL
Marc Deisenroth
Rika Antonova: Adaptive Kernels and Priors for Data-efficient Bayesian Optimization
This talk will describe a framework for constructing simulation-based kernels for ultra data-efficient Bayesian optimization (BO). We …
February 25, 2020 12:30 — 13:00
AI Centre, UCL
Marc Deisenroth
Michael Lutter: Inductive Biases for Learning Robot Control
In order to leave the factory floors and research labs, future robots must abandon their stiff and pre-programmed movements and be …
February 20, 2020 15:00 — 16:00
AI Centre, UCL
Alexander Terenin
Slides
2019
Vincent Adam: Doubly Sparse Variational Gaussian Processes
The use of Gaussian process models is typically limited to datasets with a few tens of thousands of observations due to their …
October 31, 2019 10:00 — 11:00
AI Centre, UCL
Marc Deisenroth
PDF
Samuel Kaski: Probabilistic Modelling with Experts
I will discuss multiple-data-source prediction and modelling problems arising in a number of fields, for instance in omics-based …
October 4, 2019 10:30 — 11:30
LT 139 (Huxley), Imperial College London
Marc Deisenroth
PDF
Christian Walder: New Tricks for Estimating Gradients of Expectations
We derive a family of Monte Carlo estimators for gradients of expectations, which is related to the log-derivative trick, but involves …
September 30, 2019 11:00 — 12:00
LT 130 (Huxley), Imperial College London
Marc Deisenroth
PDF
Emtiyaz Khan: Learning-Algorithms from Bayesian Principle
In machine learning, new learning algorithms are designed by borrowing ideas from optimization and statistics followed by an extensive …
September 16, 2019 14:00 — 15:00
Huxley LT 144, Imperial College London
Riccardo Moriconi
,
Marc Deisenroth
Slides
Cite
×