Presentation
Integreat is Norway’s Centre for Knowledge-Driven Machine Learning, a centre of excellence launched in 2023 as a collaboration between UiO, the Norwegian Computing Center, and UiT. August and Sigurd, among the first PhD fellows, will introduce Integreat and their current work. The centre aims to make machine learning more sustainable, accurate, trustworthy, and ethical through interdisciplinary research across multiple themes, offering PhD students a unique environment with diverse expertise and perspectives.
Speakers
August Arnstad works with Bayesian neural networks, aiming to design prior distributions that can guide the networks to a sparse solution. Bayesian machine learning is not yet up to par with the traditional frequentist methods, but can deliver uncertainty quantification which makes attractive when looking to make ML more trustable.
Sigurd Holmsen is working on the information bottleneck, a method of data compression that retains relevant data and discards irrelevant data for a machine learning task. This work combines statistics, information theory, and machine learning to span a wide range of applications.
Program
11:30 – Doors open and lunch is served
12:00 – "Research at Integreat – From Priors to Bottlenecks" by August Arnstad (PhD Candidate, Statistics and Data Science) and Sigurd Holmsen (PhD Candidate, Research Group for Digital Signal Processing and Image Analysis)
This event is open for all students, PhD candidates, postdocs, and everyone else who is interested in the topic. No registration needed.
About the seminar series
Once a month, dScience will invite you to join us for lunch and professional talks at the Science Library. In addition to these, we will serve lunch in our lounge in Kristine Bonnevies house every Thursday. Due to limited space (40 people), this will be first come, first served. See how to find us here.
Our lounge can also be booked by PhDs and Postdocs on a regular basis, whether it is for a meeting or just to hang out – we have fresh coffee all day long!