Preliminary Program

Monday January 18, 2021 Mini Deep Learning School

Location: Digitally

10:00 Introduction to Convolutional Neural Networks, Arnt-Børre Salberg

12:30 A brief introduction to generative adversarial networks and practical use cases, Håkon Hukkelås

13:20 Uncertainty Quantification in Deep Neural Networks, Fabian Brickwedde

14:15 Deep Learning in NLP, Lilja Øvrelid, Jeremy Barnes

Tuesday January 19, 2021

Location: Digitally

09:00 Opening, Michael Kampffmeyer

09:20 Keynote: Explainable machine learning - recent results and open problems, Lars Kai Hansen (Session chair: Robert Jenssen, UiT)

10:05 Coffee break

10:30-11:30 Oral Session (Narada Dilp Warakagoda, FFI)

10:30 Talk: An Empirical Study on the Robustness of Layerwise Relevance Propagation, Kristine Hein

10:50 Talk: Robust Deep Interpretable Features for Binary Image Classification, Robert Hu

11:10 Talk: Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series, Kristoffer Wickstrøm

11:30 Lunch

12:30 Keynote: Promising directions in multi-object tracking, Laura Leal-Taixé (Session chair: Michael Kampffmeyer, UiT)

13:15 Short break

13:30-14:30 Oral Session (Rudolf Mester, NTNU)

13:30 Talk: Seafloor Pipeline Detection With Deep LearningVemund Sigmundson Schøyen, Narada Dilp Warakagoda

13:50 Talk: A Tomographic Reconstruction Method using Coordinate-based Neural Network with Spatial Regularization, Jakeoung Koo

14:10 Talk: Consistent and accurate estimation of stellar parameters from HARPS-N Spectroscopy using Deep Learning, Frederik Boe Hüttel

14:30 Coffee break

15:00 Keynote: Multiple approaches with deep-learning for localising and scoring fungal pulmonary disease in lung CT scans, Elsa D. Angelini (Session chair: Arnt-Børre Salberg, NR)

15:50 Social activity

Wednesday January 20, 2021

Location: Digitally

09:00 Keynote: Generative computer vision approaches for fashion, Roland Vollgraf (Session chair: Anne Solberg, UiO)

09:45 Coffee break

10:10-11:10 Oral Session (Aase Reyes, OsloMet)

10:10 Talk: Deep domain adaptation applied to automatic fish age prediction, Alba Ordonez

10:30 Talk: Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective, Daniel J. Trosten

10:50 Talk: Semi-supervised Semantic Segmentation in Multi-frequency Echosounder Data, Changkyu Choi

11:10 Lunch

12:30-13:10 Oral Session (Daniel Romero, UiA)

12:30 Talk: Extracting Probabilistic Deterministic Finite Automata from a RNN trained on locally sourced traffic-data, Hans Martin

12:50 Talk: Extracting Horn Theories with Queries and Counterexamples, Cosimo Persia

13:10 Coffee break

13:30 Keynote: Generalized Energy-Based Models, Arthur Gretton (Session chair: Robert Jenssen, UiT)

14:15 Coffee break

14:40-15:20 Oral Session (Ana Ozaki, UiB)

14:40 Talk: SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation, Qinghui Liu

15:00 Talk: Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images, Luigi Luppino

15:20 Short break

15:30 NORA Panel Discussion (Moderator: Klas Pettersen, NORA)

16:30 Closing