Aug
28
12:00 PM12:00

WEDNESDAY lunch: Azzeddine Bakdi

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Speaker: Azzeddine Bakdi, Postdoc, Statistics and Data Science, UiO

Location: Spiseriet at Norsk Regnesentral.

Title: Multiple vessel collision and grounding risk identification through historical AIS data and adaptive safety domains.

Abstract: The growth in maritime traffic and recent technological development of autonomous navigation systems have induced an increasing attention to navigational safety in which new tools are required to automatically identify risky and complex navigation situations to avoid disastrous consequences and promote safety. Smart technology for autonomous navigation however needs to be evaluated and very extensively tested against realistic situations before autonomous vessels might be certified for sailing. In this work, real historical big maritime data sources (AIS, vessel registry, weather, maps, sea levels/ states, etc.) are investigated to identify likely situations of high risk and complexity to design a complete set of test bed scenarios for autonomous vessel evaluation. Collision, grounding, and combined risks are automatically identified from data through the design of maneuverability-dependent adaptive ship-safety-domains with spatial risk functions. The high efficiency ensures real implementation for multiple vessel risk identification over a large scale in space and time, with a promising performance that allows for risk prediction and complexity analysis against multi-criteria conflicting and uncertain navigation rules.

 

azzedine-bakdi.jpg
View Event →
Sep
11
12:00 PM12:00

WEDNESDAY lunch: Rebecca Wiborg Seyfarth

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Speaker: Rebecca Wiborg Seyfarth, Data Scientist at Cognite AS

Location: 8. floor Niels Henrik Abel’s building.

Title:

Abstract:

rebecca-wiborg.jpg
View Event →
Sep
25
12:00 PM12:00

WEDNESDAY lunch: Andreas Buschermöhle

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Speaker: Andreas Buschermöhle, Head of Data Science, Lyric

Location: Spiseriet at Norsk Regnesentral.

Title:

Abstract:

andreas-buschermohle.jpg
View Event →
Oct
9
12:00 PM12:00

WEDNESDAY lunch: Berent Lunde

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Speaker: Berent Lunde, PhD, Universitet i Stavanger

Location: 8. floor Niels Henrik Abel’s building.

Title:

Abstract:

berent-lunde.jpg
View Event →

Jun
5
12:00 PM12:00

WEDNESDAY lunch: Michael Kampffmeyer

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Speaker: Michael Kampffmeyer, Postdoc, Machine learning group, University of Tromsø

Location: Spiseriet at Norsk Regnesentral.

Title: Rethinking Knowledge Graph Propagation for Zero-Shot Learning

Abstract: Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, multi-layer architectures, which are required to propagate knowledge to distant nodes in the graph, dilute the knowledge by performing extensive Laplacian smoothing at each layer and thereby consequently decrease performance. In order to still enjoy the benefit brought by the graph structure while preventing dilution of knowledge from distant nodes, we propose a Dense Graph Propagation (DGP) module with carefully designed direct links among distant nodes. DGP allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node's relationship to its ancestors and descendants. A weighting scheme is further used to weigh their contribution depending on the distance to the node to improve information propagation in the graph. Combined with finetuning of the representations in a two-stage training approach our method outperforms state-of-the-art zero-shot learning approaches.

michael.png
View Event →
Feb
28
1:30 PM13:30

THURSDAY Biostatistics Seminar (Joint Sven Furberg Seminar): Dr. Elana Fertig and Dr. Francesca Buffa

Speakers: Dr. Elana Fertig, Associate Professor of Oncology and Applied Mathematics and Statistics Assistant Director of the Sydney Kimmel Comprehensive Cancer Center, Johns Hopkins University, Baltimore, USA, and
Dr. Francesca Buffa, Associate Professor, Computational Biology and Integrative Genomics, Department of Oncology, CRUK/MRC Institute, University of Oxford
Location: Hagen 1+2 room, Forskningsparken

View Event →