Zobrazeno 1 - 10
of 445
pro vyhledávání: '"Hansen, Lars Kai"'
Much machine learning research progress is based on developing models and evaluating them on a benchmark dataset (e.g., ImageNet for images). However, applying such benchmark-successful methods to real-world data often does not work as expected. This
Externí odkaz:
http://arxiv.org/abs/2406.09981
Autor:
Tětková, Lenka, Scheidt, Teresa Karen, Fogh, Maria Mandrup, Jørgensen, Ellen Marie Gaunby, Nielsen, Finn Årup, Hansen, Lars Kai
Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based explainability methods is constru
Externí odkaz:
http://arxiv.org/abs/2404.07008
Autor:
Madsen, Anders Gjølbye, Lehn-Schiøler, William Theodor, Jónsdóttir, Áshildur, Arnardóttir, Bergdís, Hansen, Lars Kai
Deep learning models are complex due to their size, structure, and inherent randomness in training procedures. Additional complexity arises from the selection of datasets and inductive biases. Addressing these challenges for explainability, Kim et al
Externí odkaz:
http://arxiv.org/abs/2307.12745
Autor:
Savcisens, Germans, Eliassi-Rad, Tina, Hansen, Lars Kai, Mortensen, Laust, Lilleholt, Lau, Rogers, Anna, Zettler, Ingo, Lehmann, Sune
Publikováno v:
Nature Computational Science 4 (2024) 43-56
Over the past decade, machine learning has revolutionized computers' ability to analyze text through flexible computational models. Due to their structural similarity to written language, transformer-based architectures have also shown promise as too
Externí odkaz:
http://arxiv.org/abs/2306.03009
In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through attention
Externí odkaz:
http://arxiv.org/abs/2306.00561
Autor:
Tětková, Lenka, Brüsch, Thea, Scheidt, Teresa Karen, Mager, Fabian Martin, Aagaard, Rasmus Ørtoft, Foldager, Jonathan, Alstrøm, Tommy Sonne, Hansen, Lars Kai
Current work on human-machine alignment aims at understanding machine-learned latent spaces and their correspondence to human representations. G{\"a}rdenfors' conceptual spaces is a prominent framework for understanding human representations. Convexi
Externí odkaz:
http://arxiv.org/abs/2305.17154
Autor:
Tětková, Lenka, Hansen, Lars Kai
As the use of deep neural networks continues to grow, understanding their behaviour has become more crucial than ever. Post-hoc explainability methods are a potential solution, but their reliability is being called into question. Our research investi
Externí odkaz:
http://arxiv.org/abs/2304.08984
Bayesian optimization (BO) is a popular method for black-box optimization, which relies on uncertainty as part of its decision-making process when deciding which experiment to perform next. However, not much work has addressed the effect of uncertain
Externí odkaz:
http://arxiv.org/abs/2301.05983
Preparing thermal states on a quantum computer can have a variety of applications, from simulating many-body quantum systems to training machine learning models. Variational circuits have been proposed for this task on near-term quantum computers, bu
Externí odkaz:
http://arxiv.org/abs/2111.03935
Autor:
Fetic, Raluca Alexandra, Jordahn, Mikkel, Lima, Lucas Chaves, Egebæk, Rasmus Arpe Fogh, Nielsen, Martin Carsten, Biering, Benjamin, Hansen, Lars Kai
For a multilingual podcast streaming service, it is critical to be able to deliver relevant content to all users independent of language. Podcast content relevance is conventionally determined using various metadata sources. However, with the increas
Externí odkaz:
http://arxiv.org/abs/2109.12306