50 citations · 97 across the 7 of their papers we have counts for
7 papers
Safe exploration in reproducing kernel Hilbert spaces
Abdullah Tokmak, Kiran G. Krishnan, Thomas B. Schön +1
Popular safe Bayesian optimization (BO) algorithms learn control policies for safety-critical systems in unknown environments. However, most algorithms make a smoothness assumption…
PACSBO: Probably approximately correct safe Bayesian optimization
Abdullah Tokmak, Thomas B. Schön, Dominik Baumann
Safe Bayesian optimization (BO) algorithms promise to find optimal control policies without knowing the system dynamics while at the same time guaranteeing safety with high probabi…
End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks
Theogene Habineza, Antônio H. Ribeiro, Daniel Gedon +3
Background: Atrial fibrillation (AF) is one of the most common cardiac arrhythmias that affects millions of people each year worldwide and it is closely linked to increased risk of…
Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filters
Conor Rosato, Vincent Beraud, Paul Horridge +2
It has been widely documented that the sampling and resampling steps in particle filters cannot be differentiated. The {\itshape reparameterisation trick} was introduced to allow t…
Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness
Antônio H. Ribeiro, Koen Tiels, Luis A. Aguirre +1
The exploding and vanishing gradient problem has been the major conceptual principle behind most architecture and training improvements in recurrent neural networks (RNNs) during t…
Reliable Semi-Supervised Learning when Labels are Missing at Random
Xiuming Liu, Dave Zachariah, Johan Wågberg +1
Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed…
Data Consistency Approach to Model Validation
Andreas Svensson, Dave Zachariah, Petre Stoica +1
In scientific inference problems, the underlying statistical modeling assumptions have a crucial impact on the end results. There exist, however, only a few automatic means for val…