Low-dimensional representation learning for temporal data
Title: Low-dimensional representation learning for temporal data
DNr: Berzelius-2024-140
Project Type: LiU Berzelius
Principal Investigator: Daniel Gedon <daniel.gedon@it.uu.se>
Affiliation: Uppsala universitet
Duration: 2024-03-28 – 2024-10-01
Classification: 10201
Homepage: https://mp.uu.se/web/profilsidor/start/-/emp/N19-1795


This project will support the experiments for projects in three main directions: (1) theory of deep learning. Here, we develop new theories and try to verify this on experimental benchmark data. This includes low-dimensional representation learning. (2) identification of dynamic systems with various deep learning-based methods such as deep state-space systems and graph neural networks. (3) Learning of low-dimensional representations from time series data to identify the data generating process.