Zobrazeno 1 - 10
of 171
pro vyhledávání: '"Schmidt, Mikkel"'
Autor:
Brüsch, Thea, Wickstrøm, Kristoffer K., Schmidt, Mikkel N., Jenssen, Robert, Alstrøm, Tommy S.
State-of-the-art methods for explaining predictions based on time series are built on learning an instance-wise saliency mask for each time step. However, for many types of time series, the salient information is found in the frequency domain. Adopti
Externí odkaz:
http://arxiv.org/abs/2411.05841
Contrastive learning yields impressive results for self-supervision in computer vision. The approach relies on the creation of positive pairs, something which is often achieved through augmentations. However, for multivariate time series effective au
Externí odkaz:
http://arxiv.org/abs/2410.19842
Existing communication hardware is being exerted to its limits to accommodate for the ever increasing internet usage globally. This leads to non-linear distortion in the communication link that requires non-linear equalization techniques to operate t
Externí odkaz:
http://arxiv.org/abs/2410.16125
This paper investigates the application of end-to-end (E2E) learning for joint optimization of pulse-shaper and receiver filter to reduce intersymbol interference (ISI) in bandwidth-limited communication systems. We investigate this in two numerical
Externí odkaz:
http://arxiv.org/abs/2409.11980
Autor:
Wedenborg, Anna Emilie J., Harborg, Michael Alexander, Bigom, Andreas, Elmgreen, Oliver, Presutti, Marcus, Råskov, Andreas, Glückstad, Fumiko Kano, Schmidt, Mikkel, Mørup, Morten
This paper introduces a novel framework for Archetypal Analysis (AA) tailored to ordinal data, particularly from questionnaires. Unlike existing methods, the proposed method, Ordinal Archetypal Analysis (OAA), bypasses the two-step process of transfo
Externí odkaz:
http://arxiv.org/abs/2409.07934
Autor:
Brüsch, Thea, Wickstrøm, Kristoffer Knutsen, Schmidt, Mikkel N., Alstrøm, Tommy Sonne, Jenssen, Robert
Time-series data are fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision making. To develop explainable artificial intelligence in these domain
Externí odkaz:
http://arxiv.org/abs/2406.13584
We numerically demonstrate that joint optimization of FIR based pulse-shaper and receiver filter results in an improved system performance, and shorter filter lengths (lower complexity), for 4-PAM 100 GBd IM/DD systems.
Comment: 4 pages (3 artic
Comment: 4 pages (3 artic
Externí odkaz:
http://arxiv.org/abs/2405.13367
In machine learning energy potentials for atomic systems, forces are commonly obtained as the negative derivative of the energy function with respect to atomic positions. To quantify aleatoric uncertainty in the predicted energies, a widely used mode
Externí odkaz:
http://arxiv.org/abs/2312.04174
Labeling of multivariate biomedical time series data is a laborious and expensive process. Self-supervised contrastive learning alleviates the need for large, labeled datasets through pretraining on unlabeled data. However, for multivariate time seri
Externí odkaz:
http://arxiv.org/abs/2307.09614
In federated learning, data heterogeneity is a critical challenge. A straightforward solution is to shuffle the clients' data to homogenize the distribution. However, this may violate data access rights, and how and when shuffling can accelerate the
Externí odkaz:
http://arxiv.org/abs/2306.13263