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:
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.
A novel progressive training algorithm for learning Graph Neural Networks with Differential Privacy guarantees
Dockerized AI4EU Acumos component for uncertainty estimation for classification networks
Verifiable and Explainable RIsk Forecasting Artificial Intelligence Framework
Federated training of Graph Neural Networks (GNNs) with Local Differential Privacy
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...
REST web service simulating the Wumpus World intelligent agent environment popularised by Russell & Norvig's seminal textbook Artificial Intelligence: A Modern Approach.
Current solutions to legal translation are based on machine learning techniques. Such techniques are based on statistics and always exhibit a margin of error. In addition, machine learning, which is based on data and algorithms, is by definition unethical...
This repository contains the base components necessary to bootstrap your own Constraint Object-Oriented Logic Action Programming as a Service (COOLAPS) application docker container.
