research
∙
09/18/2023
Application-driven Validation of Posteriors in Inverse Problems
Current deep learning-based solutions for image analysis tasks are commo...
share
research
∙
10/21/2022
Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition
Reliably estimating the uncertainty of a prediction throughout the model...
research
∙
04/13/2022
Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity
Many real-world systems are described not only by data from a single sou...
research
∙
03/15/2022
Trustworthy Deep Learning via Proper Calibration Errors: A Unifying Approach for Quantifying the Reliability of Predictive Uncertainty
With model trustworthiness being crucial for sensitive real-world applic...
research
∙
07/08/2021
Encoding Domain Information with Sparse Priors for Inferring Explainable Latent Variables
Latent variable models are powerful statistical tools that can uncover r...
research
∙
06/08/2021
Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems
Recommender systems are often designed based on a collaborative filterin...
research
∙
02/24/2021
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
We address the problem of uncertainty calibration and introduce a novel ...
research
∙
01/23/2021
Hierarchical Domain Invariant Variational Auto-Encoding with weak domain supervision
We address the task of domain generalization, where the goal is to train...
research
∙
12/20/2020
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
We address the problem of uncertainty calibration. While standard deep n...
research
∙
12/20/2020
Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration
To facilitate a wide-spread acceptance of AI systems guiding decision ma...
research
∙
07/10/2020
TIMELY: Improving Labeling Consistency in Medical Imaging for Cell Type Classification
Diagnosing diseases such as leukemia or anemia requires reliable counts ...
research
∙
01/15/2020
AAAI FSS-19: Human-Centered AI: Trustworthiness of AI Models and Data Proceedings
To facilitate the widespread acceptance of AI systems guiding decision-m...
research
∙
10/09/2018
textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior
We address two challenges of probabilistic topic modelling in order to b...
research
∙
10/09/2018
textTOvec: Deep Contextualized Neural Autoregressive Models of Language with Distributed Compositional Prior
We address two challenges of probabilistic topic modelling in order to b...
research
∙
09/15/2018
Document Informed Neural Autoregressive Topic Models with Distributional Prior
We address two challenges in topic models: (1) Context information aroun...
research
∙
08/11/2018