Search Results for author:
Found 8 papers, 0 papers with code
Developing trustworthy AI applications with foundation models
Chapter 2 provides an introduction to the technical construction of foundation models and Chapter 3 shows how AI applications can be developed based on them.
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.
Using ScrutinAI for Visual Inspection of DNN Performance in a Medical Use Case
We use our VA tool to analyse the influence of label variations between different experts on the model performance.
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.
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.
Communication-Efficient Distributed Online Learning with Kernels
It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion.
Adaptive Communication Bounds for Distributed Online Learning
The learning performance of such a protocol is intuitively optimal if approximately the same loss is incurred as in a hypothetical serial setting.
