Home - CERTAIN | Center for Explainable Transparant and Theory-Driven AI in the Netherlands

Center for Explainable
Responsible and Theory-driven Artificial Intelligence

Trustworthy

Trustworthy

We let more and more of our daily life be influenced by AI technology. But can we trust the technology to handle this influence with care?

Responsible

Responsible

"Responsible AI" is an approach for generating and evaluating AI systems that act in a “responsible manner” (e.g., avoid being “responsible” for harms).

Verifiable

Verifiable

Verified AI technology comes with guarantees that it does what it is supposed to do, without fail. For "verifiable AI" technology, we can make assessments about whether it comes with such guarantees.

Language Models

Language Models

Language models are computer programs designed to understand (and to generate) human text, based on word patterns that it learned from being exposed to many texts.

Fairness

Fairness

The term “fairness” covers a multitude of different concepts. Choosing the right notion of fairness for a specific AI system presents a formidable research challenge.

Bias

Bias

“Bias” in the context of AI usually means a (hidden) flaw in the way a computer system makes decisions causing it to systematically provide undesirable outputs.

Explainable

Explainable

“Explainable AI” is the subfield of AI concerned with providing explanations for how AI systems arrive at their predictions, decisions or other output.

Inclusive

Inclusive

"Inclusive AI" is about advocating for AI that is developed by and for everyone, in order to design just and empowering technologies.

Algorithms

Algorithms

An "algorithm" is traditionally defined as a set of instructions for performing a task.

Theory-driven

Theory-driven

Theory-driven AI emphasizes the necessity for truly understanding current AI systems, and for building future AI systems that are efficient, explainable and trustworthy.

Trustworthy

Trustworthy

We let more and more of our daily life be influenced by AI technology. But can we trust the technology to handle this influence with care?

Responsible

Responsible

"Responsible AI" is an approach for generating and evaluating AI systems that act in a “responsible manner” (e.g., avoid being “responsible” for harms).

Verifiable

Verifiable

Verified AI technology comes with guarantees that it does what it is supposed to do, without fail. For "verifiable AI" technology, we can make assessments about whether it comes with such guarantees.

Language Models

Language Models

Language models are computer programs designed to understand (and to generate) human text, based on word patterns that it learned from being exposed to many texts.

Fairness

Fairness

The term “fairness” covers a multitude of different concepts. Choosing the right notion of fairness for a specific AI system presents a formidable research challenge.

Bias

Bias

“Bias” in the context of AI usually means a (hidden) flaw in the way a computer system makes decisions causing it to systematically provide undesirable outputs.

Explainable

Explainable

“Explainable AI” is the subfield of AI concerned with providing explanations for how AI systems arrive at their predictions, decisions or other output.

Inclusive

Inclusive

"Inclusive AI" is about advocating for AI that is developed by and for everyone, in order to design just and empowering technologies.

Algorithms

Algorithms

An "algorithm" is traditionally defined as a set of instructions for performing a task.

Theory-driven

Theory-driven

Theory-driven AI emphasizes the necessity for truly understanding current AI systems, and for building future AI systems that are efficient, explainable and trustworthy.

Browse research content

These are samples of research projects, papers or blogs written by our researchers.

InDeep: Interpreting Deep Learning Models for Text and Sound

Goal of the project is to find ways to make popular Artificial Intelligence models for language, speech and music more...

How robust and reliable can we expect language models to be?

This paper investigates robustness in how we measure performance of language models like ChatGPT. If you were to ask a...

Going beyond a mathematical investigation of bias

A version of this blog post first appeared on https://odvanderwal.nl/2023/positioning-bias. When researchers study how biased language models are, they generally approach...

Blogs & events

Using Language Sciences for Social Good

Language technologies, like ChatGPT, are developing quickly. But we don’t really know how they work. And they are not always designed to help society. adapted from Nikki Weststeijn‘s post on...

Going beyond a mathematical investigation of bias

A version of this blog post first appeared on https://odvanderwal.nl/2023/positioning-bias. When researchers study how biased language models are, they generally approach this in a mathematical or statistical way. For example,...

More information
about CERTAIN