Technologies

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?

With AI becoming more prolific in society, the need for human-machine teaming (i.e

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

Image classification is a branch of computer vision that focuses on categorizing and labelling groups of pixels.

Knowledge modelling is a cross-disciplinary field that focuses on how to capture, preserve, and apply existing knowledge.

Machine learning is a subfield of artificial intelligence. It focuses on the creation of algorithms which can extract information from data to learn new behavior

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.

Secure learning is an umbrella term for various methods that all focus on the creation of secure algorithm which can extract information from data while preserving its confidentiality.

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