Zobrazeno 1 - 10
of 24 188
pro vyhledávání: '"Micha, A."'
We revisit the recently developed framework of proportionally fair clustering, where the goal is to provide group fairness guarantees that become stronger for groups of data points (agents) that are large and cohesive. Prior work applies this framewo
Externí odkaz:
http://arxiv.org/abs/2410.23273
To further improve Lithium-ion batteries (LiBs), a profound understanding of complex battery processes is crucial. Physical models offer understanding but are difficult to validate and parameterize. Therefore, automated machine-learning methods (ML)
Externí odkaz:
http://arxiv.org/abs/2410.19478
Video capsule endoscopy has transformed gastrointestinal endoscopy (GIE) diagnostics by offering a non-invasive method for capturing detailed images of the gastrointestinal tract, enabling early disease detection. However, its potential is limited by
Externí odkaz:
http://arxiv.org/abs/2410.21302
Autor:
Bradač, Domagoj, Christoph, Micha
A folklore result attributed to P\'olya states that there are $(1 + o(1))2^{\binom{n}{2}}/n!$ non-isomorphic graphs on $n$ vertices. Given two graphs $G$ and $H$, we say that $G$ is a unique subgraph of $H$ if $H$ contains exactly one subgraph isomor
Externí odkaz:
http://arxiv.org/abs/2410.16233
G-structures and Cartan geometries are two major approaches to the description of geometric structures (in the sense of differential geometry) on manifolds of some fixed dimension $n$. We show that both descriptions naturally extend to the setting of
Externí odkaz:
http://arxiv.org/abs/2410.10410
We propose a new variant of the strategic classification problem: a principal reveals a classifier, and $n$ agents report their (possibly manipulated) features to be classified. Motivated by real-world applications, our model crucially allows the man
Externí odkaz:
http://arxiv.org/abs/2410.08032
Autor:
Venkatesh, Danush Kumar, Rivoir, Dominik, Pfeiffer, Micha, Kolbinger, Fiona, Speidel, Stefanie
In computer-assisted surgery, automatically recognizing anatomical organs is crucial for understanding the surgical scene and providing intraoperative assistance. While machine learning models can identify such structures, their deployment is hindere
Externí odkaz:
http://arxiv.org/abs/2410.07753
Large conferences such as NeurIPS and AAAI serve as crossroads of various AI fields, since they attract submissions from a vast number of communities. However, in some cases, this has resulted in a poor reviewing experience for some communities, whos
Externí odkaz:
http://arxiv.org/abs/2410.03474
Autor:
Wasem, Micha, Yerly, Florence
In this work, we present a novel approach to type design by using Fourier-type series to generate letterforms. We construct a Fourier-type series for functions in $L^2(S^1,\mathbb C)$ based on triangles of constant width instead of circles to model t
Externí odkaz:
http://arxiv.org/abs/2409.11958
Computer-assisted surgery (CAS) systems are designed to assist surgeons during procedures, thereby reducing complications and enhancing patient care. Training machine learning models for these systems requires a large corpus of annotated datasets, wh
Externí odkaz:
http://arxiv.org/abs/2408.09822