On Wednesday 28 February, our former UT colleague Meike Nauta will visit the UT and give two presentations. The slot 14.00-15.45 is dedicated for networking, raising ideas and establishing new collaborations. Please find below the details of our program, which consists of two parts.
Program
| 12:00 | Walk-in & sandwiches for external guests and staff members. |
| 12:45 | Presentation for staff members and (industrial) stakeholders by Meike Nauta: Quo Vadis, Explainable AI? |
| 14:00 | Start interactive program: open mic, pitches external guests and staff |
| 15:00 | Closing of the session – room for after-talk, introductions and networking. |
| 15:45 | Guest lecture for students and other interested colleagues by Meike Nauta: Explainable AI: what is it, why do we need it and what makes a good explanation? |
| 17:30 | Finish |
Whereas the guest lecture was originally implemented in the master course Information Systems. Other students, interested PhDs, PostDocs and other colleagues are highly encouraged to join this inspiring lecture!
Abstract
12.45 – Quo Vadis, Explainable AI? Foremostly aimed at stakeholders and staff.
Explainable AI is about opening up the black box and giving users insight into the underlying reasoning of an AI model. It is relevant to a broad range of stakeholders and applications, and therefore a rising research field both internationally and at the UT.
Meike Nauta will give an overview of explainable AI methods, while showing both the possibilities and risks of using them. She will then present her view on the future of explainable and responsible AI: interpretability-by-design and "AI with premeditation" (Dutch: "AI met voorbedachten rade"). Meike will end the talk with highlighting research gaps and opportunities, to give a head start to the networking and brainstorming part of the session.
15.45 – Explainable AI: what is it, why do we need it and what makes a good explanation? Guest lecture for students, open to everybody.
Explainable AI (XAI) methods aim to explain black-box machine learning models and thereby give users insight into the model's decision-making process. Meike Nauta will introduce explainable AI and show why XAI should be more than "nice to have". But, can we trust explainable AI methods if they are black boxes themselves?
Meike will present explainable-by-design models as an alternative for the black box, in line with her vision for responsible AI: power to the people with the power of AI.
Meike Nauta
Meike Nauta is a senior data scientist at Datacation in Eindhoven and obtained her PhD in explainable AI and interpretable computer vision (cum laude) at the University of Twente in 2023. She developed novel AI models that can be understood and adapted by humans. Her pioneering work on interpretable AI has been published at top AI venues including CVPR, IJCAI and ACM Computing Surveys. She is among the national top 5 Women in AI Young Professionals, included in the tech talent list T500 and has won the ZEISS Women in IT award in 2022.
Location
