Zobrazeno 1 - 10
of 3 335
pro vyhledávání: '"Gossmann, A"'
Genetic diversity is central to the process of evolution. Both natural selection and random genetic drift are influenced by the level of genetic diversity of a population; selection acts on diversity while drift samples from it. At a given locus in a
Externí odkaz:
http://arxiv.org/abs/2411.06431
Autor:
Sun, Xudong, Feistner, Carla, Gossmann, Alexej, Schwarz, George, Umer, Rao Muhammad, Beer, Lisa, Rockenschaub, Patrick, Shrestha, Rahul Babu, Gruber, Armin, Chen, Nutan, Boushehri, Sayedali Shetab, Buettner, Florian, Marr, Carsten
Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization l
Externí odkaz:
http://arxiv.org/abs/2403.14356
Autor:
Sun, Xudong, Chen, Nutan, Gossmann, Alexej, Xing, Yu, Feistner, Carla, Dorigatt, Emilio, Drost, Felix, Scarcella, Daniele, Beer, Lisa, Marr, Carsten
We address the online combinatorial choice of weight multipliers for multi-objective optimization of many loss terms parameterized by neural works via a probabilistic graphical model (PGM) for the joint model parameter and multiplier evolution proces
Externí odkaz:
http://arxiv.org/abs/2403.13728
Machine learning (ML) algorithms can often differ in performance across domains. Understanding $\textit{why}$ their performance differs is crucial for determining what types of interventions (e.g., algorithmic or operational) are most effective at cl
Externí odkaz:
http://arxiv.org/abs/2402.14254
Publikováno v:
Diversity and Distributions, 2024 May 01. 30(5), 1-13.
Externí odkaz:
https://www.jstor.org/stable/48769313
Autor:
Feng, Jean, Subbaswamy, Adarsh, Gossmann, Alexej, Singh, Harvineet, Sahiner, Berkman, Kim, Mi-Ok, Pennello, Gene, Petrick, Nicholas, Pirracchio, Romain, Xia, Fan
After a machine learning (ML)-based system is deployed, monitoring its performance is important to ensure the safety and effectiveness of the algorithm over time. When an ML algorithm interacts with its environment, the algorithm can affect the data-
Externí odkaz:
http://arxiv.org/abs/2311.11463
Autor:
Feng, Jean, Gossmann, Alexej, Pirracchio, Romain, Petrick, Nicholas, Pennello, Gene, Sahiner, Berkman
In a well-calibrated risk prediction model, the average predicted probability is close to the true event rate for any given subgroup. Such models are reliable across heterogeneous populations and satisfy strong notions of algorithmic fairness. Howeve
Externí odkaz:
http://arxiv.org/abs/2307.15247
Autor:
Rita Rosner, Rebekka Eilers, Katharina Gossmann, Johanna Kneidinger, Katharina Szota, Hanna Christiansen, Sebastian Deutscher, Christina Schulte, David Daniel Ebert, Anne Grass, Sophie Rueger, Rainer Muche, Anna-Carlotta Zarski, Regina Steil
Publikováno v:
European Journal of Psychotraumatology, Vol 15, Iss 1 (2024)
Background: The implementation trial BESTFORCAN aims to evaluate the dissemination of Trauma-Focused Behavioural Therapy (TF-CBT) for children and adolescents in Germany with posttraumatic stress symptoms (PTSS) after child abuse and neglect (CAN) wi
Externí odkaz:
https://doaj.org/article/2a42d7109b294550846efd5c1698b661
Autor:
Jérémy Amossé, Rima Souki, Maguy El Hajjar, Marie Marques, Valentine Genêt, Alexis Février, Morgane Le Gall, Benjamin SaintPierre, Franck Letourneur, Eric Le Ferrec, Dominique Lagadic-Gossmann, Christine Demeilliers, Lydie Sparfel
Publikováno v:
Ecotoxicology and Environmental Safety, Vol 285, Iss , Pp 117065- (2024)
Exposure to polycyclic aromatic hydrocarbons (PAHs), ubiquitously environmental contaminant, leads to the development of major toxic effects on human health, such as carcinogenic and immunosuppressive alterations reported for the most studied PAH, i.
Externí odkaz:
https://doaj.org/article/1b407791d61841db8c2e4541123ec996
Autor:
Feng, Jean, Gossmann, Alexej, Pennello, Gene, Petrick, Nicholas, Sahiner, Berkman, Pirracchio, Romain
Performance monitoring of machine learning (ML)-based risk prediction models in healthcare is complicated by the issue of confounding medical interventions (CMI): when an algorithm predicts a patient to be at high risk for an adverse event, clinician
Externí odkaz:
http://arxiv.org/abs/2211.09781