Search Results for author:
Found 12 papers, 2 papers with code
Assessing Systematic Weaknesses of DNNs using Counterfactuals
With the advancement of DNNs into safety-critical applications, testing approaches for such models have gained more attention.
Guideline for Trustworthy Artificial Intelligence -- AI Assessment Catalog
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society.
A Survey on Uncertainty Toolkits for Deep Learning
The success of deep learning (DL) fostered the creation of unifying frameworks such as tensorflow or pytorch as much as it was driven by their creation in return.
Tailored Uncertainty Estimation for Deep Learning Systems
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable.
Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis
We propose a novel framework consisting of a generative label-to-image synthesis model together with different transferability measures to inspect to what extent we can transfer testing results of semantic segmentation models from synthetic data to equivalent real-life data.
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods.
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities
To address this constraint, we present an approach to detect learned shortcuts using an interpretable-by-design network as a proxy to the black-box model of interest.
Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation
Data-driven sensor interpretation in autonomous driving can lead to highly implausible predictions as can most of the time be verified with common-sense knowledge.
A Novel Regression Loss for Non-Parametric Uncertainty Optimization
One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice.
Wasserstein Dropout
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved.
DenseHMM: Learning Hidden Markov Models by Learning Dense Representations
We propose two optimization schemes that make use of this: a modification of the Baum-Welch algorithm and a direct co-occurrence optimization.
Characteristics of Monte Carlo Dropout in Wide Neural Networks
Monte Carlo (MC) dropout is one of the state-of-the-art approaches for uncertainty estimation in neural networks (NNs).
