PhD student Rwiddhi Chakraborty at UiT
Image:
Robert Jenssen

PhD student Rwiddhi Chakraborty at UiT

Joint Doctoral Course between UiO and UiT

Self Supervised Explainability on Graphs

Joint Doctoral Course between UiO and UiT: Self Supervised Explainability on Graphs

In the past decade, the availability of large-scale datasets allowed the proliferation of deep learning-based architectures in computer vision, language modelling, and graph-based data. The curation and annotation process of these datasets is overly expensive. In recent years, new methodologies emerged to train deep learning models on unlabeled data, so called self-supervision.

Online discussion, Screenshot by Adín Ramírez Rivera

To prepare students on these highly relevant topics, we, University of Oslo (UiO) and UiT The Arctic University of Norway (UiT), as part of the SFI Visual Intelligence efforts, joined forces to teach a special curriculum course about bleeding edge topics related to deep learning methods based on self-supervision and non-structured data (that is, based on graphs). Moreover, due to the need to reveal the decisions made by these models, we placed special emphasis on novel techniques used to explain the inner workings of these models.

The course puts an emphasis on letting the student discuss and lead the learning endeavor. The sessions encompassed active discussions among the participants. Professors from UiO and UiT provided useful moderation and insights to the discussions. William Ho, a UiO masters’ student, mentioned, “this [course] has been the most enjoyable course I’ve ever taken [at] IFI,” due to its highly interactive setup. Also, Rwiddhi Chakraborty, from UiT, expressed the usefulness of the curriculum and discussions. Another anonymous student mentions, “[presenting papers to each other] has been fantastic to complete the learning cycle—since we are learning the content and then presenting/teaching it as well.”

The wonderful experience has already led to innovative ideas on improving collaboration between the two sites and will be integrated into future offerings of the course. After seeing the success and enthusiasm from the students, we will explore new ways of providing more joint venues for the students to collaborate between the two sites.

Responsible at UiT: Michael Kampffmeyer

Responsable at UiO: Adín Ramírez Rivera

Latest news

Visual Intelligence keynote at the 2022 Norwegian AI Society Conference

June 9, 2022

Director Robert Jenssen gave the keynote "Visual Intelligence advances deep learning research towards innovations" at the 2022 Norwegian AI Society Conference (NAIS) in Oslo.

Pitch-day for ideas for master’s projects for the computer science and machine learning students at UiT

April 19, 2022

We invited companies, the public sector, and other organizations to present their ideas for master’s projects and to connect with students having an interest and background in computer science and machine learning.

Talk about Ethics in AI at the Aim North 2022 conference

April 6, 2022

Director Robert Jenssen gave a talk about explainable AI connected to the overarching theme of the Aim North conference, namely Ethics in AI. The talk outlined e.g. VI's recent results on detecting artifacts in medical images by our "Prototypical Relevance Propagation" method.

Talk by VI's Director Robert Jenssen at the opening of the Pioneer AI Centre

March 29, 2022

The Pioneer AI Centre is Denmark's flagship centre on AI, headed by prof. Serge Belongie, University of Copenhagen/KU. The official opening of the centre took place March 28 2022 at the "Black Diamond" in Copenhagen city centre.

Transforming ocean surveying by the power of DL and statistical methods

March 28, 2022

New project associated with Visual Intelligence on reduce bottlenecks related to uncertainty estimates in classification by a combined statistical and machine learning approach. The project is on recognition of specific objects at and within the seabed from several image types.

Visual Intelligence is a central partner in NORA research school - a new national PhD School

March 25, 2022

The Visual Intelligence Graduate School (VIGS) will be an important component in the NORA research school and Visual Intelligence's Northern Lights Deep Learning (NLDL) conference will be a venue for winter school activities within this nation-wide initiative.

SFI Visual Intelligence guest talk by Cristina Soguero-Ruiz

March 22, 2022

Associate Professor Cristina Soguero-Ruiz visited Tromsø and gave a very interesting talk on March 17th 2022 on how to exploit AI and machine learning for medical image analysis and healthcare applications.

New associated project on offshore wind energy

February 25, 2022

Through the ongoing Akademia Avtale fund between Equinor and UiT. The goal is to develop new innovative approaches for combining image data and other sources of information in the context of wind energy.

Program for Visual Intelligence Days 2021

October 15, 2021

The "Visual Intelligence days" is coming up shortly, and VI-collaborators will gather in Oslo to connect and share knowledge. Phd-students and early career researchers will also gather one day in advance to socialize. Please see the updated program.

How is AI affecting democratic processes?

October 4, 2021

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?“.