Seminars and posters
As we publish novel research we often present our work at conferences, during poster sessions and at various seminars. When presentations and talks are filmed we will publish them here, so they can be viewed by everyone.
How is AI affecting democratic processes?
Visual Intelligence director Robert Jenssen gave a talk and participated in a panel debate organized by the Norwegian Academy of Science and Letters on the topic “How is AI affecting democratic processes?“.
Presentation at Eurpoean Conference on Machine Learning 2021
Norwegian Artificial Intelligence Research Consotrium podcast on artificial intelligence
Norway Health Tech's webinar 2020: Digitalization of the health sector towards 2025
Norway Health Tech hosted a national webinar with the goal of illuminating possibilities for artificial intelligence in the health sector. Professor Robert Jenssen was invited to present Visual Intelligence's strategy for research and development. The webinar can be found here.
BigMed-conference 2020: The road to precision medicine19th October 2020
The BigMed project is funded by the Norwegian Research Council and a handful of dedicated partners. It is a consortium that is led from Oslo University Hospital and includes academic and industrial partners, as well as patient organizations.
They hosted the BigMed-conference 2020 in Oslo the 19th October the aim was to highlight the barriers of implementation within precision medicine in clinical practice, and how these challenges could be addressed. The conference hosted some of Norway's most recognized experts within the field. Robert Jenssen from the Machine Learning Group was invited to participate in a channel discussion at the conference. Link to the broadcasted conference (Norwegian) can be found here.
Medical imaging and machine learning12th October 2020
Erik Smistad, NTNU and SINTEF Medical Techonology,
Sathiesh Kaliyugarasan, MMIV, Haukeland University Hospital
Robert Jenssen, Machine Learning Group at UiT
How can machine learning be used in diagnostics and other medical imaging tasks?
Some of the biggest and most important leaps in modern machine learning has been within the field of image analysis. The three speakers give a presentation of the potential of the use of machine learning in medical imaging at the Tekna webinar. Link to the webinar (Norwegian).
NORA.startup digital kick-off29th September 2020
Norwegian Artificial Intelligence Research Consortium (NORA) recently launched NORA.startup. A gateway for greater cooperation between academia, incubators and startup companies in the field of artificial intelligence, machine learning and robotics.
At the kick-off of NORA.startup various speakers related to the project presented several interesting and related topics. Robert Jenssen from the UiT Machine Learning Group and center leader for Visual Intelligence was a panelist at the kick-off. He gave a presentation on Research-driven Innovations and how to facilitate innovations in industry. The news article from NORA and the recorded kick-off can be found here.
SEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks
Poster presentation: Van Nhan NguyenAugust 2020
We equip Prototypical Networks (PNs) with a novel dissimilarity measure to enable discriminative feature normalization for few-shot learning. The embedding onto the hypersphere requires no direct normalization and is easy to optimize. Our theoretical analysis shows that the proposed dissimilarity measure, denoted the Squared root of the Euclidean distance and the Norm distance (SEN), forces embedding points to be attracted to its correct prototype, while being repelled from all other prototypes, keeping the norm of all points the same. The resulting SEN PN outperforms the regular PN with a considerable margin, with no additional parameters as well as with negligible computational overhead.
A generic unfolding algorithm for manifolds estimated by local linear approximations
Poster presentation: Jonas Nordhaug MyhreJune 2020
Manifold learning is one of the fundamental directions of Machine Learning research. It is motivated by the notion that high dimensional data sets often exhibit intrinsic structure that is concentrated on or near manifolds of lower local dimensionality. However, the problem of unwrapping or unfolding manifolds has received relatively little attention despite being an integral part of manifold learning in general. In this work, we present a new generic algorithm for unfolding manifolds that have been estimated by local linear approximations. Our algorithm is a combination of ideas from principal curves and density ridge estimation and tools from classical differential geometry.
New advances in deep learning with applications in the monitoring of power lines
Robert Jenssen at NORA8th May 2020
This talk with Robert Jenssen (UiT The Arctic University of Norway) describes novel deep learning methodological research conducted at the UiT Machine Learning Group in collaboration with the company eSmart Systems.
The motivation for the work is an industrial project where the aim is to monitor power lines from UAV images using specially developed deep convolutional neural networks. The talk describes a proposed neural network called the LS-Net for segmenting out line structures corresponding to power lines. Furthermore, inspired by the power line monitoring problem, the talk describes new basic research within so-called few-shot learning, proposing a new similarity measure to regularize such systems for better performance.
Machine learning and artificial intelligence for decision support by innovative analysis of electronic health records
Robert Jenssen at Hemit conference 2019 (Norwegian)19th September 2019
Robert Jenssen gives a talk at the Hemit conference of 2019 about machine learning applications in the medical domain. The talk focuses on the research of the Machine Learning Group at UiT and their novelties related to data-driven decision support based on electronic health records and the use of artificial intelligence to detect post-operative delirium.