Technologies

A Bayesian network is a probabilistic graphical model that can be used to describe (causal) relations between random variables in complex technical systems. Queries about the system can be answered with inference techniques that are grounded in probability theory

Recent methods developed for explainable Artificial Intelligence (XAI) visualize or show an ordered list about how much data elements contribute to an outcome. If there are many input data elements, this kind of explanation can become difficult to comprehend when there are many contributing data elements or features

Counterfactual fairness is a definition of fairness that states that an algorithm is counterfactual fair if its results for an individual would be the same in a world where she belongs to another (counterfactual) sociodemographic group. An algorithm that is used for recruitment is counterfactual fair if selecting a person for a job interview is equally probable if (s)he were a man, woman, ethnic minority or ethnic majority

Explainable Artificial Intelligence deals with how AI models can be explained and understood by humans to improve the interaction, usability and trust.

Can we obtain a **fair** classification model based on a biased dataset? How?

Standard machine learning pradigms like supervised and unsupervised learning assume the data to be available as a tabular dataset. In practical applications the data can be spread in various distributed databases

Hybrid AI offers the potential to combine two different paradigms in AI: knowledge-based reasoning and data-driven machine learning.

Secure Multi-Party Computation (MPC) is a set of cryptographic techniques that allow for generating functionality for federated databases without the need to copy the data to a central database. Conceptually the functionality works as if the data were in a central database, while the cryptographic measures ensure data confidentiality

Many applications of decision-making involve a trade-off between multiple criteria or objectives. For example, decision-making algorithms in autonomous vehicles must make a trade-off between safety and journey time while algorithms for fraud detection have to make a trade-off between fairness and financial losses

NLP combines the techniques of statistics with machine learning. This makes it possible to extract keywords from a text

SONNET is TNO's Semantic Ontology Engineering Toolset and has the goal to assist humans in developing taxonomies or ontologies.

For safe deployment of automated vehicles on the public road, the AI systems in the vehicle should be aware of their own competence in the current situation, and act more cautiously or hand over to the driver in situations where the AI is uncertain.

Deep learning models rely on large annotated datasets in order to obtain good results. However, in many domains such as the security and healthcare domains there is a lack of large annotated datasets due to the high cost and long time needed to acquire and/or label relevant data

Word embedding is a technology in Natural Language Processing (NLP). The aim is to have a represenation of text into a vector space, where semantically similar texts are close to each other