2.9k citations · 12k across the 144 of their papers we have counts for
22 papers · 1 filter
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Angelos Filos, Sebastian Farquhar, Aidan N. Gomez +6
Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' unce…
FDL: Mission Support Challenge
Luís F. Simões, Ben Day, Vinutha M. Shreenath +4
The Frontier Development Lab (FDL) is a National Aeronautics and Space Administration (NASA) machine learning program with the stated aim of conducting artificial intelligence rese…
Adversarial recovery of agent rewards from latent spaces of the limit order book
Jacobo Roa-Vicens, Yuanbo Wang, Virgile Mison +2
Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challeng…
Auto-Calibration of Remote Sensing Solar Telescopes with Deep Learning
Brad Neuberg, Souvik Bose, Valentina Salvatelli +6
As a part of NASA's Heliophysics System Observatory (HSO) fleet of satellites,the Solar Dynamics Observatory (SDO) has continuously monitored the Sun since2010. Ultraviolet (UV) an…
Using U-Nets to Create High-Fidelity Virtual Observations of the Solar Corona
Valentina Salvatelli, Souvik Bose, Brad Neuberg +6
Understanding and monitoring the complex and dynamic processes of the Sun is important for a number of human activities on Earth and in space. For this reason, NASA's Solar Dynamic…
Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics & Losses
Anna Jungbluth, Xavier Gitiaux, Shane A. Maloney +7
Breakthroughs in our understanding of physical phenomena have traditionally followed improvements in instrumentation. Studies of the magnetic field of the Sun, and its influence on…
Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
Xavier Gitiaux, Shane A. Maloney, Anna Jungbluth +7
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific do…
Machine Learning for Generalizable Prediction of Flood Susceptibility
Chelsea Sidrane, Dylan J Fitzpatrick, Andrew Annex +3
Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood model…
Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder
Kara Lamb, Garima Malhotra, Athanasios Vlontzos +7
High energy particles originating from solar activity travel along the the Earth's magnetic field and interact with the atmosphere around the higher latitudes. These interactions o…
Prediction of GNSS Phase Scintillations: A Machine Learning Approach
Kara Lamb, Garima Malhotra, Athanasios Vlontzos +7
A Global Navigation Satellite System (GNSS) uses a constellation of satellites around the earth for accurate navigation, timing, and positioning. Natural phenomena like space weath…
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl +4
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions…
Flood Detection On Low Cost Orbital Hardware
Gonzalo Mateo-Garcia, Silviu Oprea, Lewis Smith +5
Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much t…
Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control
Rhiannon Michelmore, Matthew Wicker, Luca Laurenti +3
Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to thei…
Generalizing from a few environments in safety-critical reinforcement learning
Zachary Kenton, Angelos Filos, Owain Evans +1
Before deploying autonomous agents in the real world, we need to be confident they will perform safely in novel situations. Ideally, we would expose agents to a very wide range of…
Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning
Sebastian Farquhar, Michael Osborne, Yarin Gal
We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space…
Towards Inverse Reinforcement Learning for Limit Order Book Dynamics
Jacobo Roa-Vicens, Cyrine Chtourou, Angelos Filos +3
Multi-agent learning is a promising method to simulate aggregate competitive behaviour in finance. Learning expert agents' reward functions through their external demonstrations is…
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Andreas Kirsch, Joost van Amersfoort, Yarin Gal
We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple…
An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval
Adam D. Cobb, Michael D. Himes, Frank Soboczenski +7
Machine learning is now used in many areas of astrophysics, from detecting exoplanets in Kepler transit signals to removing telescope systematics. Recent work demonstrated the pote…
Learning Sparse Networks Using Targeted Dropout
Aidan N. Gomez, Ivan Zhang, Siddhartha Rao Kamalakara +4
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning proce…
Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
Mike Walmsley, Lewis Smith, Chris Lintott +10
We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN…
Differentially Private Continual Learning
Sebastian Farquhar, Yarin Gal
Catastrophic forgetting can be a significant problem for institutions that must delete historic data for privacy reasons. For example, hospitals might not be able to retain patient…
A Unifying Bayesian View of Continual Learning
Sebastian Farquhar, Yarin Gal
Some machine learning applications require continual learning - where data comes in a sequence of datasets, each is used for training and then permanently discarded. From a Bayesia…