What we're about
Interested in the use of artificial intelligence for innovation? We focus on technology, on academic-industrial collaboration, and on sharing the outcomes of ICAI's labs.
Upcoming events (4)
In September, ICAI: The Labs is focused on AI for Autonomous Systems in the Netherlands. The EAISI AIMM lab and Delta lab each present their work and discuss challenges and developments in this field.
The EAISI AI-enabled Manufacturing and Maintenance (AIMM) Lab is a collaboration between Eindhoven University of Technology (TU/e), KMWE, Lely, Marel, and Nexperia. The lab's goal is to improve decision-making in manufacturing and maintenance using artificial intelligence. AIMM Lab is based in Eindhoven.
The UvA and Bosch have agreed to extend their established research lab. Delta Lab 2 - the follow-up to the successful collaboration Delta Lab 1 - will focus on the use of artificial intelligence and machine learning for applications in computer vision, generative models and causal learning.
12.00 (noon) Opening by Esther Smit (ICAI, UvA)
12:05 Introduction of the EAISI AIMM lab by Geert-Jan van Houtum (TU Eindhoven) , followed by his presentation "A Predictive Maintenance Concept for Geographically Dispersed Technical Systems"
12.45 Discussion of what’s next in AI for Autonomous Systems
"A Predictive Maintenance Concept for Geographically Dispersed Technical Systems"
Thanks to IoT, it is nowadays possible to remotely monitor the health status of technical systems. This information can be used to come to a so-called predictive maintenance concept. Under such a concept, the aim is to replace a degrading component by a ready-for-use component just before a failure would occur. This can be done for components for which you can follow the degradation behavior or for which you can predict upcoming failures by some form of data analysis. For other components, you may only have information on the lifetime distribution and replacement decisions have to be taken based on the age of the component. A system has generally a mix of components: lifetimes are given for a first group of components, degradation processes for a second group of components, and data- based failure predictions for a third group of components. In addition, many systems are geographically dispersed and require an expensive visit of a service engineer for the execution of maintenance. Then maintenance actions for the various components have to be clustered in order to avoid high costs for engineer visits. We show how an appropriate predictive maintenance concept can be constructed for geographically dispersed technical systems. We will include a case at a manufacturer of agricultural high-tech equipment.
"On the Calibration of Systems that Learn to Defer to Experts"
Learning to defer (L2D) systems offer a promising solution to the problem of AI safety. For a given input, the system can defer the decision to a human if the human is more likely than the model to take the correct action. We study the calibration of L2D systems, investigating if the probabilities they output are sound. We find that Mozannar & Sontag’s (2020) multiclass framework is not calibrated with respect to expert correctness. Moreover, it is not even guaranteed to produce valid probabilities due to its parameterization being degenerate for this purpose. We propose an L2D system based on one-vs-all classifiers that is able to produce calibrated probabilities of expert correctness. Furthermore, our loss function is also a consistent surrogate for multiclass classification, like Mozannar & Sontag’s (2020). In addition to being calibrated, our model exhibits accuracy that is comparable to Mozannar & Sontag’s (2020) model (and often better) in tasks ranging from hate speech detection to galaxy classification to diagnosis of skin lesions.
*To participate sign up here
The collaboration between ‘location technology specialist’ TomTom and the University of Amsterdam (UvA) started in September 2020, however, due to the corona crisis, the Atlas Lab has had to wait until now to host its first event. This means they have exciting research to showcase the use of AI to develop advanced, highly accurate and safe high definition (HD) maps for self-driving vehicles.
The program features:
- Academic keynote by prof. dr. Daniel Cremers from Technical University of Munich;
- Overview of the Atlas Lab by lab manager dr. Martin Oswald and Atlas PhD students;
- Presentation by Corinne Vigreux (Co-Founder and CMO at Tomtom);
- Opening ceremony by prof. dr. Geert T.M. ten Dam (Chair Executive Board UvA) and prof. dr. Alfons Hoekstra (director Informatics Institute).
We cordially invite you to the official opening on Thursday 15 September 2022 from 15:00 to 16:45 (with drinks and networking 16:45-18:00) at Amsterdam Startup Village, Science Park 608, Amsterdam.
More details on the program will be shared in the coming weeks.
ICAI Launch Pad:
ICAI has initiated the Launch Pad together with the Netherlands AI Coalition with the aim to connect AI talent with organizations in the Dutch ecosystem by providing a matchmaking process between AI-PhD students and Dutch companies looking for AI talent. There are no costs involved for the students. We do this on a non-profit basis.
We believe that the Netherlands offers great opportunities in the field of AI for our top AI experts.
13:00 (noon): Opening
13:02 "Diversity career paths for STEM PhDs: science policy, data science, technology consulting, and entrepreneurship" by Katherine Liu Slater (Technical SETA)
13:20 First Q& A
13:30 The Second Career Talk
13:45: Second Q& A
"Diversity career paths for STEM PhDs: science policy, data science, technology consulting, and entrepreneurship."
- Why not academic:
- Personal experience in science policy, data science, technology consulting, and entrepreneurship.
- Supporting public policy with data science
- Environmental monitoring
- Fishery management
- The critical skills for having an impactful industrial career, even if your research is niche specific, are problem-solving, synthesis and analysis, communication, and networking
On the 6th of October, between 12:00 and 13:00, ‘ ICAI: The Labs’ will have a meetup on AI for computer vision in the Netherlands. Two labs each present their work and discuss challenges and developments in this field.
QUVA Lab is the collaboration between Qualcomm and the University of Amsterdam. The mission of the QUVA-lab is to perform world-class research on deep vision. Such vision strives to automatically interpret with the aid of deep learning what happens where, when, and why in images and video.
Thira Lab is a collaboration between Thirona, Delft Imaging Systems, and Radboud UMC. The mission of the lab is to perform world-class research to strengthen healthcare with innovative imaging solutions.
12.00 (noon): Opening
12:05 Introduction of the QUVA Lab by Yuki Asano (UvA)
12:10 QUVA Lab: Philip Lippe (UvA) about: “CITRUS: Causal Identifiability from Temporal Sequences with Interventions”
12:25 Introduction of the Thira Lab by Keelin Murphy (Radboudumc)
12:30 2nd technical by Thira lab
12.45 Discussion of what’s next in AI in Computer Vision in the Netherlands
“CITRUS: Causal Identifiability from Temporal Sequences with Interventions”
Understanding the underlying causal factors of a dynamical system is a crucial step towards agents reasoning in complex environments. Recent progress in causal representation learning and non-linear ICA showed that, in certain situations like factors being independent, it is possible to uncover such factors from observations. We seek to extend this line of work to a temporal domain where interventions have been performed on a subset of variables in between time steps, which resembles the setting of an agent taking actions over time. We propose CITRUS, a variational autoencoder framework which, with the help of interventional data, can identify the causal variables up to their intervention-dependent aspects and all remaining information. Further, CITRUS can be extended to pretrained autoencoders, opening up future research areas of simulation-to-real-world generalization for causal learning. Evaluated on visually complex image sequences with non-linear relations among causal variables, the method is capable to disentangle and recover the underlying causal variables.