Zobrazeno 1 - 10
of 1 551
pro vyhledávání: '"A. Gregorová"'
Recently, several methods have leveraged deep generative modeling to produce example-based explanations of decision algorithms for high-dimensional input data. Despite promising results, a disconnect exists between these methods and the classical exp
Externí odkaz:
http://arxiv.org/abs/2410.20890
To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from classifiers, especially those not trained on noisy images, are often un
Externí odkaz:
http://arxiv.org/abs/2406.17399
Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of thes
Externí odkaz:
http://arxiv.org/abs/2308.06100
Despite advances in generative methods, accurately modeling the distribution of graphs remains a challenging task primarily because of the absence of predefined or inherent unique graph representation. Two main strategies have emerged to tackle this
Externí odkaz:
http://arxiv.org/abs/2306.07735
Autor:
Monika Vlachová, Lukáš Pečinka, Jana Gregorová, Lukáš Moráň, Tereza Růžičková, Petra Kovačovicová, Martina Almáši, Luděk Pour, Martin Štork, Roman Hájek, Tomáš Jelínek, Tereza Popková, Marek Večeřa, Josef Havel, Petr Vaňhara, Sabina Ševčíková
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
Abstract Multiple myeloma (MM) is the second most prevalent hematological malignancy, characterized by infiltration of the bone marrow by malignant plasma cells. Extramedullary disease (EMD) represents a more aggressive condition involving the migrat
Externí odkaz:
https://doaj.org/article/123756e52c444a3ba9395eee02fa6b55
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features
Externí odkaz:
http://arxiv.org/abs/2212.00449
Publikováno v:
Autonomous Intelligent Systems, Vol 4, Iss 1, Pp 1-10 (2024)
Abstract The generation and optimization of simulation data for electrical machines remain challenging, largely due to the complexities of magneto-static finite element analysis. Traditional methodologies are not only resource-intensive, but also tim
Externí odkaz:
https://doaj.org/article/cb481940fcac4021800c9e5bdf4015f7
Autor:
Benjamin Gagl, Klara Gregorová
Publikováno v:
npj Science of Learning, Vol 9, Iss 1, Pp 1-12 (2024)
Abstract Efficient reading is essential for societal participation, so reading proficiency is a central educational goal. Here, we use an individualized diagnostics and training framework to investigate processes in visual word recognition and evalua
Externí odkaz:
https://doaj.org/article/070e0cb590c4441eb4828209de9e472d
Publikováno v:
Open Ceramics, Vol 19, Iss , Pp 100658- (2024)
Silica refractories are promising materials for high-temperature thermal energy storage (HT-TES), because they exhibit excellent thermal cycling properties, unless cooled below a critical temperature (usually assumed to be 600 °C). When cooling down
Externí odkaz:
https://doaj.org/article/51a3fbdfd5aa43d1afdaad7e598a9d30
Autor:
Gregorová, Eva, Pabst, Willi, Šimonová, Petra, Nečina, Vojtěch, Kotrbová, Lucie, Bezdička, Petr, Hubálková, Jana, Schmidt, Gert, Aneziris, Christos G., Sedlářová, Ivona, Kotouček, Miroslav
Publikováno v:
In Journal of the European Ceramic Society February 2025 45(2)