Search Results for author:
Found 10 papers, 9 papers with code
Bayesian Semi-structured Subspace Inference
To this end, we extend subspace inference for joint posterior sampling from a full parameter space for structured effects and a subspace for unstructured effects.
Single-shot Bayesian approximation for neural networks
We demonstrate that our single-shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BNNs.
Bayesian Calibration of MEMS Accelerometers
This study aims to investigate the utilization of Bayesian techniques for the calibration of micro-electro-mechanical systems (MEMS) accelerometers.
Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows
The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control.
Bernstein Flows for Flexible Posteriors in Variational Bayes
Variational inference (VI) is a technique to approximate difficult to compute posteriors by optimization.
Transformation Models for Flexible Posteriors in Variational Bayes
In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distributions.
Deep and interpretable regression models for ordinal outcomes
We present ordinal neural network transformation models (ONTRAMs), which unite DL with classical ordinal regression approaches.
Integrating uncertainty in deep neural networks for MRI based stroke analysis
For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the single image-level predictions.
Single Shot MC Dropout Approximation
We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.
Deep transformation models: Tackling complex regression problems with neural network based transformation models
Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number.
