Sustainability and Machine Learning Group
Sustainability and Machine Learning Group
Home
Team
Publications
Blog
Teaching
Talks
News
Openings
1
Optimal Transport for Offline Imitation Learning
With the advent of large datasets, offline reinforcement learning is a promising framework for learning good decision-making policies …
Yicheng Luo
,
Zhengyao Jiang
,
Samuel Cohen
,
Edward Grefenstette
,
Marc P. Deisenroth
Cite
PDF
Reviews
Code
Actually Sparse Variational Gaussian Processes
A typical criticism of Gaussian processes is their unfavourable scaling in both compute and memory requirements. Sparse variational …
Jake Cunningham
,
Daniel Augusto de Souza
,
So Takao
,
Mark van der Wilk
,
Marc P. Deisenroth
Cite
PDF
Code
Transfer and zero-shot learning for weed species detection with small datasets and unseen classes
Nicolas Belissent
,
Jose Manuel Peña
,
Gustavo Mesı́as-Ruiz
,
John, Pérez-Ortiz, Maria Shawe-Taylor
Cite
Actually Sparse Variational Gaussian Processes
In this work, we propose a new class of inter-domain variational Gaussian process, constructed by projecting onto a set of compactly …
Jake Cunningham
,
So Takao
,
Mark van der Wilk
,
Marc P. Deisenroth
Cite
Optimal Transport for Offline Imitation Learning
With the advent of large datasets, offline reinforcement learning is a promising framework for learning good decision-making policies …
Yicheng Luo
,
Zhengyao Jiang
,
Samuel Cohen
,
Edward Grefenstette
,
Marc P. Deisenroth
Cite
URL
Short-term Prediction and Filtering of Solar Power Using State-Space Gaussian Processes
Short-term forecasting of solar photovoltaic energy (PV) production is important for powerplant management. Ideally these forecasts are …
So Takao
,
Sean Nassimiha
,
Peter Dudfield
,
Jack Kelly
,
Marc P. Deisenroth
Cite
URL
One-Shot Transfer of Affordance Regions? AffCorrs!
In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance …
Denis Hadjivelichkov
,
Sicelukwanda Zwane
,
Lourdes Agapito
,
Marc P. Deisenroth
,
Dimitrios Kanoulas
Cite
PDF
Blog
Bayesian Optimization based Nonlinear Adaptive PID Design for Robust Control of the Joints at Mobile Manipulators
In this paper, we propose to use a Nonlinear Adaptive PID controller to regulate the joint variables of a mobile manipulator. Motion of …
Hadi Hajieghrary
,
Marc P. Deisenroth
,
Yasemin Bekiroğlu
Cite
Comparing the carbon costs and benefits of low-resource solar nowcasting
Ben Dixon
,
Jacob Bieker
,
Marı́a Pérez-Ortiz
Cite
Parallel MCMC Without Embarrassing Failures
Embarrassingly parallel Markov Chain Monte Carlo (MCMC) exploits distributed computing to scale Bayesian inference to large datasets by …
Daniel Augusto de Souza
,
Diego Mesquita
,
Samuel Kaski
,
Luigi Acerbi
Cite
«
»
Cite
×