16th May, Spring meeting 2023: Robust AI
On Tuesday 16th of May 2023 we hope to see you all again in Nijmegen for an afternoon around Robust AI.
We have to make sure AI systems are robust when we want to apply them in the real world. To have trust in their decisions, we like these explainable. We want them to handle unmodelled phenomena in a predictive way. We want to make sure that the models are correct and without bias. Human user errors should not throw them off course. We can not model the whole real world, so we should think about predictable and unpredictable unknowns.
In another inspiring afternoon, we are going to explore these important questions with three invited keynote speakers:
- Geert Litjens ( Radboud UMC, Nijmegen )
- Nicola Pezzotti ( Philips Cardiologs, Paris )
- Nicola Strisciuglio ( University of Twente, Enschede )
And we will have a series of short research presentations again.
You are invited to submit your abstract (max. 1 A4 plus 1 or 2 illustrations) for a short oral or posterpresentation. Please submit your abstract before 1 May, 2023 as PDF to secretary@nvphbv.nl. You will receive a notice of acceptance by 8 May, 2023. Topics include, but are not limited to: Robust AI in ComputerVision and Image Processing, Pattern Recognition, Deep Learning, Neural Networks.
By doing so you might win the best-abstract award of €200. Furthermore this is the first time the abstracts for a NVPHBV meeting will be published in online proceedings.
As always there will be ample time to connect with all attendees from industry and academia.
Due to increasing costs we have to ask a small fee of 20/40 euros (members/non-members) for attendance.
Just use the register button to grab your ticket soon.
photocredit: https://depositphotos.com/stock-photos/art-objects.html
Hourly Schedule
Spring Meeting 2023
- 12:00 - 13:20
- Lunch & Poster Session
- 13:00 - 13:20
- General Assembly Meeting (NVPHBV members only)
- Our yearly assembly meeting of the society
- 13:20 - 14:10
- Keynote: Robust and transparent AI in computational pathology
-
Speakers:
Dr. Geert Litjens
- 14:10 - 15:00
- Abstract Presentations
- Prof. Clarisa Sánchez
- 15:00 - 15:30
- Break - Coffee & Tea
- 15:30 - 16:20
- Keynote: Trustworthy iterative deep-learning models and … hot air balloons
-
Speakers:
Dr. Nicola Pezzotti
- 16:20 - 17:10
- Curse and bless of bias: identifying, mitigating and inducing it in computer vision
-
Speakers:
Dr. Nicola Strisciuglio
- 17:10 - 17:15
- Abstract Award Ceremony
- Prof. Clarisa Sánchez
- 17:15 - 18:30
- Drinks & Networking
Speakers
-
Dr. Geert LitjensAssistant professor at Radboud UMC
Geert Litjens is an assistant professor of Computational Pathology at Radboud University Medical Center and co-chairs the Computation Pathology Group. He applies modern machine learning methods to oncological pathology, leading research projects in areas such as prostate and pancreatic cancer. Litjens studied Biomedical Engineering at Eindhoven University of Technology and completed his PhD on Computer-aided detection of prostate cancer at Radboud University Medical Center. He has been awarded several Dutch and European grants and awards, including an ERC Starting Grant and a KNAW Early Career Award. Litjens is a member of the MIDL Board and the editorial board of Medical Image Analysis. He also organizes challenges in medical image analysis, such as PROMISE12, CAMELYON, and PANDA.
-
Dr. Nicola StrisciuglioAssistant Professor at University of Twente
Nicola Strisciuglio is an Assistant Professor at the Faculty of Electrical Engineering, Mathematics and Computer Science of the University of Twente (Netherlands). He received the Ph.D. degree cum laude in Computer Science from the University of Groningen (Netherlands) and the University of Salerno (Italy). He has been general co-chair of five editions of the International Conference on Applications of Intelligent Systems (APPIS). His research interests include machine learning and computer vision, focusing on the identification of sources of bias or the exploitation of inductive bias to make more robust and generalizable computer vision models.
-
Dr. Nicola PezzottiPhilips Cardiologs Paris and TU Eindhoven
Nicola Pezzotti is Director of Data Science at Philips Cardiologs in Paris and an assistant professor at the Eindhoven University of Technology. His research interests include machine learning, medical imaging, visual analytics, explainable AI, optimization techniques, and software engineering. He received his BSc and MSc degrees in Computer Science and Engineering from the University of Brescia, Italy, in 2009 and 2011. He received his PhD cum Laude from Delft University of Technology, the Netherlands, in 2018. Besides his experience in the startup world, he was a visiting scientist to INRIA Saclay, Paris, in 2017 and Google AI, Zurich, in 2018. He is the recipient of several awards, including the IEEE VGTC Best Dissertation Award, TU Delft Excellence in Research, and the Dirk Bartz Prize for Visual Computing in Medicine.