Monday January 10, 2022 Tutorials and Industry & Women in AI Events

Location: GatherTown, Main Lecture Room (all times are in CET)

09:45 Pre-tutorial Information (Michael Kampffmeyer, UiT)

10:00 - 15:00 Tutorials

The tutorial session will consist of three tutorials that cover recent topics in Deep Learning.

10:00 - 11:30 Tutorial I: Deep Learning in Biomedical Imaging, Pierre Baldi (University of California, Irvine). Session Chair: Alba Ordonez (NR)

12:20 - 13:50 Tutorial II: Intro to Graph Machine Learning, Benjamin Ricaud, Filippo Bianchi (UiT), Nicolas Aspert (EPFL), Volodymyr Miz (INAIT). Session Chair: Cristina Soguero Ruíz (URJC)

14:15 - 15:00 Tutorial III: The Information Bottleneck Approaches in Deep Neural Networks, Shujian Yu (UiT). Session Chair: Ahcene Boubekki (UiT)

Location: GatherTown, Industry/Women in AI room (all times are in CET)

15:00 - 16:45 Industry Event (NLDL Event hosted by NORA and Visual Intelligence)

The Industry event will address important subjects such as why artificial intelligence is important for industry, how AI can provide additional value to industry, the problems that AI can potentially solve and how academia and industry should collaborate on facilitating the safe and sustainable use of AI. The event will consist of short key notes given by experts in the field, and end with a panel discussion. More info here.

17:00 - 19:00 Women in AI Event (NLDL Event hosted by NORA and Visual Intelligence)

During the Women in AI event, we will bring together representatives from industry, public administration and research to address the gender disparity in AI in Norway and the world today, and discuss initiatives to ensure inclusivity and diversity in AI for the future. The session will consist of short keynotes, followed by a panel discussion. More info here.

Tuesday January 11, 2022

Location: GatherTown, Main Lecture Room (all times are in CET)

09:00 Opening (Michael Kampffmeyer, UiT)

09:15 Invited Talk 1: Pierre Baldi. Session Chair: Robert Jenssen (UiT)

10:00 Coffee break

10:30-11:30 Oral Session 1. Session Chair: Narada Dilp Warakagoda (FFI)

10:30 Talk: Detection of forest roads in Sentinel-2 images using U-Net, Øyvind Due Trier

10:50 Talk: CryoSat-2 waveform classification for melt event monitoring, Martijn Vermeer

11:10 Talk: Photo-Realistic Continuous Image Super-Resolution with Implicit Neural Networks and Generative Adversarial Networks, Muhammad Sarmad

11:30 Lunch

12:30 Invited Talk 2: Sophia Ananiadou. Session Chair: Alba Ordonez (NR)

13:15 Special Session: Deep learning for Cultural Heritage (Organized by: Irina-Mihaela Ciortan, Sony George, and Jon Yngve Hardeberg (NTNU))

13:20 Talk: Automated mapping of cultural heritage in Norway from airborne lidar data using faster R-CNN, Øyvind Due Trier

13:40 Talk: Semantic Aware Style Transfer: Preserving Artistry Relevance, Georges Roussel

14:00 Poster Session I and Coffee

15:20 Northern Lights Talk, Magnar Gullikstad Johnsen

15:55-16:35 Oral Session 2. Session Chair: Rudolf Mester (NTNU)

15:55 Talk: Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples, Li Meng

16:15 Talk: Deep Reinforcement Learning for Detection of Abnormal Anatomies, Paula López Diez

16:35 Coffee break

16:45-17:45 Oral Session 3. Session Chair: Huamin Ren (KUC)

16:45 Talk: Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach, Jonas Schulz

17:05 Talk: Extracting Rules from Neural Networks with Partial Interpretations, Cosimo Persia

17:25 Talk: Learnable filter-banks for CNN-based audio applications and their performances, Benjamin Ricaud

Wednesday January 12, 2022

Location: GatherTown, Main Lecture Room (all times are in CET)

09:00 Invited Talk 3: Marina Marie-Claire Höhne. Session Chair: Michael Kampffmeyer (UiT)

09:45 Coffee break

10:10-11:30 Oral Session 4. Session Chair: Arnt-Børre Salberg (NR)

10:10 Talk: Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning, Tosin Adewumi

10:30 Talk: Add a SideNet to your MainNet, Adrien Morisot

10:50 Talk: Mutual information estimation for graph convolutional neural networks, Marius C. Landsverk

11:10 Talk: An analysis of over-sampling labeled data in semi-supervised learning with FixMatch, Miquel Marti

11:30 Lunch

12:30 Invited Talk 4: Serge Belongie. Session Chair: Line Eikvil, NR

13:15 NORA Panel Discussion (Moderator: Klas Pettersen, NORA)

14:15 Poster Session II and Coffee

15:40-16:40 Oral Session 5. Session Chair: Ana Ozaki, UiB

15:40 Talk: Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection, Luca Tomasetti

16:00 Talk: The effect of dataset confounding on Deep Neural Networks predictions for medical imaging, Beatriz Garcia Santa Cruz

16:20 Talk: LayeredCNN: Segmenting Layers with Autoregressive Models, Jakob L. Christensen

16:40-17:20 Oral Session 6. Session Chair: Line Clemmensen, DTU

16:40 Talk: Modelling Phytoplankton Behaviour in the North and Irish Sea with Transformer Networks, Onatkut Dagtekin

17:00 Talk: Forecasting Aquaponic Systems Behaviour With Recurrent Neural Networks Models, Juan Cardenas-Cartagena

17:20 Closing (Robert Jenssen, UiT)

Poster Session 1 (Tuesday, 14:00-15:20). Session Chair: Benjamin Ricaud, UiT

#1 On the Effect of Image Statistics and Perceptual Metrics in Autoencoders, Alexander Hepburn
#2 Training with single class images and Generalizing for multi-class images using Kasami Orthogonal Classification Layer, Mohamed M, Saadeldin
#3 Sinogram-Domain Augmentation For CT Reconstruction, Wail Mustafa
#4 Compressing CNN Kernels for Videos Using Tucker Decompositions: Towards Lightweight CNN Applications, Tobias Engelhardt Rasmussen
#5 Classification of Prohibited Materials from Multi-View Spectral X-Ray Projection Images Using Deep Learning, Elise O. Brenne
#6 Studying the role of spatial context for vegetation dynamics with a convolutional and recurrent neural network, Vitus Benson
#7 Vanishing Curvature in Randomly Initialized Deep ReLU Networks, Antonio Orvieto
#8 When more is less: Adverse Effects in Outlier Exposure, Jennifer J Matthiesen
RELAX: Representation Learning Explainability, Kristoffer K. Wickstrøm
#10 Visual explanations of a deep reinforcement learning docking agent, Inga Strumke
#11 Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages, Sneha Das
#12 Monocular Depth Estimation Using Multi Scale Neural Network And Feature Fusion, Abhinav Sagar
#13 Variational Inference for Bayesian Neural Networks under Model and Parameter Uncertainty, Aliaksandr Hubin
#14 Reconsidering Representation Alignment for Multi-view Clustering, Daniel J. Trosten
#15 Unsupervised Time Series Classification for Climate Data, Alex Romanova
#16 Deep learning for underwater vegetation mapping based on UAV hyperspectral imagery, Martin H. Skjelvareid
#17 Towards Understanding of User Perceptions for Smart Border Control Technologies using a Fine-Tuned Transformer Approach, Sarang Shaikh
#18 Studying the Propagation of Information in VAE Decoders, Yannick Rudolph
#19 Explainability and Uncertainty for Mammogram Classification, Alba Ordonez

Poster Session 2 (Wednesday, 14:15-15:40). Session Chair: Sigurd Løkse, UiT

#20 Learning covariant Lyapunov vectors from data using residual networks, Christoph Martin
#21 Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision, Stine Hansen
#22 Fast accuracy estimation of deep learning based multi-class musical source separation, Alexandru Mocanu
#23 Context-Aware Landmark Detection for 2D Cardiac Ultrasound using a Graph Convolution Network, Amund Vedal
#24 A mammography classification model trained from image labels only, Fredrik Dahl
Random Signature Layers, Antonio Orvieto
#26 Analytic Insights into Structure and Rank of Neural Network Hessian Maps, Sidak Pal Singh
#27 Re-Identification of Giant Sunfish using Keypoint Matching, Malte Pedersen
#28 Artifact Detection with Prototypical Relevance Propagation, Srishti Gautam
#29 Optimizing Slimmable Networks for Multiple Target Platforms, Zifu Wang
#30 Self-Communicating Deep Reinforcement Learning Agents Develop External Number Representations, Silvester Sabathiel
#31 Segmentation of costa in 2d MRI scans utilizing the U-Net convolutional network architecture, Helge Fredriksen
#32 Translational challenges of biomedical machine learning solutions in clinical and laboratory settings, Carlos Vega
#33 LS-Weights: Local Search with Weighted Neighborhood Sampling for Neural Architecture Search, Meyssa Zouambi
#34 Surrogate-data-enriched Physics-Aware Neural Networks, Raphael Leiteritz
#35 SparseMeshCNN with Self-Attention for Segmentation of Large Meshes, Bjørn Hansen
#36 Generative Model and Goal-Conditioned Reinforcement Learning, Mariana Vargas Vieyra
#37 Segmenting Multi-frequency Marine Acoustic Data in a Semi-supervised Fashion, Changkyu Choi

NORA Panel Discussion

The Norwegian Artificial Intelligence Research Consortium – aims to strengthen Norwegian research and education within artificial intelligence, machine learning and robotics.

NORA is a collaboration between the University of Oslo (UiO), University of Bergen (UiB), University of Stavanger (UiS), The Arctic University of Norway (UiT), Oslo Metropolitan University (OsloMet), University of Agder (UiA), Norwegian University of Life Sciences (NMBU), NORCE Norwegian Research Centre AS (NORCE) and Simula Research Laboratory (Simula).

Discover Northern Lights at Sommarøy 11th January 2022

Sommarøy is a natural gem by the ocean, at the outer coast, a nice one-hour drive from Tromsø. A vibrant and traditional coastal community, where hunting, fishing, and trapping has been a part of daily life.

We invite to dinner in beautiful surroundings. The dinner will be served inside but you will have the opportunity to take a walk outside.

Experience the North-Norwegian winter with Aurora Borealis. (We hope!)

Dress code: Casual (the environment is rough but nice!)

Price: NOK 1195 per person;

Duration: 4 hours

Pickup/Drop off: Scandic Ishavshotell 18:30/23:00

Included: Transport (75 minute each way), dinner buffet, 1 glas aperetif and 1 glass of wine/beer/mineral water.

The Sommarøy Event is unfortunately canceled due to the digital nature of NLDL 2022.