Verifiable AI
The Verifiable AI objectives are organized in four open research questions that constitute four dimensions of the grand challenge resulting from the emergent use of AI in safety-critical applications. These four dimensions also represent the natural way to organize the background material on Verifiable AI:
- Dependability with AI: how to design and verify dependable and secure systems that include unverifiable AI components?
- Dependability of AI: how to verify the dependability and security of AI components themselves (i.e., domain-independent inference engines, as well as knowledge bases either machine learned from data or manually encoded by human domain experts)?
- AI for dependability: which AI techniques can be themselves leveraged to automate the design and verification of systems that include unverified AI components?
- Meta-AI dependability: which AI techniques can be themselves leveraged to automate the design and verification of AI components (meta-AI)?
Asset Type
Dataset
Vibration sensor measurements in a robotic wrist
A data set of 1.8 billion measurements from a mechanical wrist with three axes that can hold tools, for example, for spray painting in combination with a pump. The data set spans six months in 1-second intervals.
GEOSKOP SLU
Asset Type
As a Service
New generation of 6-month global forecast
Introducing ESFA (Empirical Season Forecast for Agriculture) – your reliable companion in long-term agricultural planning. Our validated AI algorithms, which outperform other state-of-the-art climate prediction models, are at the core of ESFA's capabiliti...
Asset Type
Jupyter Notebook
Fairness-Aware ML Tutorial Series
This tutorial series offers a hands-on guide to fairness-aware machine learning that targets beginners in Fair-ML.
Asset Type
Dataset
Adaptive Test Case Selection - Datasets
Data sets to evaluate test case prioritization and selection, finding test cases likely to fail.
Asset Type
ML Model
DIH4AI: X-MUC-2_Platform-as-a-service for accountable evidential transactions
In the domains of aeronautics, automotive, energy, manufacturing and retail, Munich Innovation Hub for Applied AI proposes novel solutions to counter the complexity and dependability challenges resulting from distributed accountability, the need for more ...
Asset Type
Dataset
Vibration sensor measurements in a robotic pump
A data set of 380 million measurements from a hydraulic pump that can be mounted on an industrial robot, for example, to pump liquid paint for spray painting. The data set spans two months in 1-second intervals.
Asset Type
Dataset
ULTIMATE WORKSHOP UC SYNTHETIC DATASET V1 (ROS1 NOETIC )
The ULTIMATE WORKSHOP UC SYNTHETIC DATASET V1 dataset is composed of 24 files (12 ROS1-Noetic and 12 ROS2-Humble recordings), each one containing a scene reproducing a hybrid environment populated by 3 RGBD cameras, two humans and robots. The included hum...
Asset Type
Library
TUPLES Scientific Contribution - Publications
The first objective of TUPLES was to advance the scientific state of the art in Trustworthy AI, with a focus on designing and managing safe, robust, scalable, and explainable planning and scheduling decision-support systems and tools.
Asset Type
Docker container
VERIFAI
Verifiable and Explainable RIsk Forecasting Artificial Intelligence Framework
Video file