ELLIIT Focus period on Machine Learning for Climate Science

We are organizing the ELLIIT Focus Period on Machine Learning for Climate Science which features several reserch seminars by visiting scholars during the period September 23 - October 25. For this reason there will be fewer regular ML seminars than usual during the semester. Please check the seminar schedule on the Focus period webpage.

Friday, August 30, 10:15, 2024

Anomaly detection in videos
Neelu Madan, Department of Architecture, Design and Media Technology, Aalborg University
Abstract: Anomaly detection addresses the challenge of identifying actions and events that significantly deviate from normal patterns. This field has a wide range of applications, from detecting defects in industrial inspection processes to identifying abnormal growths such as cancerous tumors in medical diagnostics, and recognizing unusual incidents in visual surveillance systems. Despite its vast practical relevance, anomaly detection remains a challenging problem, largely due to the vague and context-dependent nature of anomaly definitions. Given the challenges associated with the data labeling, many recent solutions lean towards unsupervised, self-supervised, and semi-supervised learning.
Location: Alan Turing
Organizer: Fredrik Lindsten

Thursday, September 26, 14:15, 2024

Modelling and generating data via deep probabilistic representations
Thomas Schön, Department of Information Technology, Uppsala University
Abstract: One of the key lessons to take away from contemporary machine learning is that flexible models often offer the best predictive performance. This has implications in many situations. In this talk I will try to make this concrete by looking at a few constructions that we are working with. I will start with a (classical) classification task from ECG interpretation and then continue to the more under-researched area of how to formulate and solve regression problems using deep learning. There are currently several different approaches used for deep regression and there is still room for innovation. I will illustrate this landscape in general and introduce some of our developments consisting of a deep regression method which has a clear probabilistic interpretation. When it comes to generative models I will also share some insights related to diffusion models, in particular related to its use for image restoration. Besides sharing some of our findings for this particular problem I will also point out some more general aspects we came to realize in working on this.
Location: Alan Turing
Organizer: Fredrik Lindsten

Past Seminars

Spring 2024   |   Fall 2023   |   Spring 2023   |   Fall 2022   |   Spring 2022   |   Spring 2021   |   Spring 2020   |   Fall 2019   |   Spring 2019   |   Fall 2018   |   Spring 2018   |   Fall 2017   |   Spring 2017   |   Fall 2016   |   Spring 2016  |   Fall 2015   |   Spring 2015   |   Fall 2014

The seminars are typically held every fourth Wednesday at 15.15-16.15 in Alan Turing.
For further information, or if you want to be notified about the seminars by e-mail, please contact Fredrik Lindsten.