469 citations
- Centre for Arctic Gas Hydrate, Environment and ClimateNO44 papers
- Centre National de la Recherche ScientifiqueFR28 papers
- University of OsloNO21 papers
- Norwegian Computing CenterNO16 papers
- University of WarwickGB13 papers
- University of ArizonaUS12 papers
- Technical University of DenmarkDK11 papers
- KTH Royal Institute of TechnologySE10 papers
- Massachusetts Institute of TechnologyUS10 papers
- Norwegian University of Science and TechnologyNO10 papers
- Observatoire de ParisFR10 papers
- University Hospital of North NorwayNO10 papers
13 papers · 1 filter
Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
Kristoffer Wickstrøm, Michael Kampffmeyer, Karl Øyvind Mikalsen +1
The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing…
Computationally Efficient Approximations for Matrix-based Renyi's Entropy
Tieliang Gong, Yuxin Dong, Shujian Yu +1
The recently developed matrix based Renyi's entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi definite (PSD) matrices in…
Leveraging tensor kernels to reduce objective function mismatch in deep clustering
Daniel J. Trosten, Sigurd Løkse, Robert Jenssen +1
Objective Function Mismatch (OFM) occurs when the optimization of one objective has a negative impact on the optimization of another objective. In this work we study OFM in deep cl…
Noisy multi-label semi-supervised dimensionality reduction
Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Filippo Maria Bianchi +1
Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not ac…
Deep Divergence-Based Approach to Clustering
Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi +3
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminati…
Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series
Daniel J. Trosten, Andreas S. Strauman, Michael Kampffmeyer +1
The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths. If t…