FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996373516> ?p ?o ?g. }

• W2996373516 abstract "Abstract Deep generative models, such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAs) have been demonstrated to produce images of high visual quality. However, the existing hardware on which these models are trained severely limits the size of the images that can be generated. The rapid growth of high dimensional data in many fields of science therefore poses a significant challenge for generative models. In cosmology, the large-scale, three-dimensional matter distribution, modeled with N-body simulations , plays a crucial role in understanding the evolution of structures in the universe. As these simulations are computationally very expensive, GANs have recently generated interest as a possible method to emulate these datasets, but they have been, so far, mostly limited to two dimensional data. In this work, we introduce a new benchmark for the generation of three dimensional N -body simulations, in order to stimulate new ideas in the machine learning community and move closer to the practical use of generative models in cosmology. As a first benchmark result, we propose a scalable GAN approach for training a generator of N -body three-dimensional cubes. Our technique relies on two key building blocks, (i) splitting the generation of the high-dimensional data into smaller parts, and (ii) using a multi-scale approach that efficiently captures global image features that might otherwise be lost in the splitting process. We evaluate the performance of our model for the generation of N -body samples using various statistical measures commonly used in cosmology. Our results show that the proposed model produces samples of high visual quality, although the statistical analysis reveals that capturing rare features in the data poses significant problems for the generative models. We make the data, quality evaluation routines, and the proposed GAN architecture publicly available at https://github.com/nperraud/3DcosmoGAN ." @default.
• W2996373516 created "2019-12-26" @default.
• W2996373516 creator A5018692490 @default.
• W2996373516 creator A5026330747 @default.
• W2996373516 creator A5045413165 @default.
• W2996373516 creator A5059632472 @default.
• W2996373516 creator A5060064717 @default.
• W2996373516 creator A5068049945 @default.
• W2996373516 date "2019-12-01" @default.
• W2996373516 modified "2023-10-01" @default.
• W2996373516 title "Cosmological N-body simulations: a challenge for scalable generative models" @default.
• W2996373516 cites W1481932901 @default.
• W2996373516 cites W1607535394 @default.
• W2996373516 cites W1799095182 @default.
• W2996373516 cites W1984182170 @default.
• W2996373516 cites W1997151611 @default.
• W2996373516 cites W2038989249 @default.
• W2996373516 cites W2067169601 @default.
• W2996373516 cites W2078179989 @default.
• W2996373516 cites W2097117768 @default.
• W2996373516 cites W2112791214 @default.
• W2996373516 cites W2141709306 @default.
• W2996373516 cites W2302117322 @default.
• W2996373516 cites W2442489531 @default.
• W2996373516 cites W2532287105 @default.
• W2996373516 cites W2572438701 @default.
• W2996373516 cites W2606759614 @default.
• W2996373516 cites W2738588019 @default.
• W2996373516 cites W2743474597 @default.
• W2996373516 cites W2758289058 @default.
• W2996373516 cites W2890064342 @default.
• W2996373516 cites W2897914751 @default.
• W2996373516 cites W2923557884 @default.
• W2996373516 cites W2927675713 @default.
• W2996373516 cites W2962793481 @default.
• W2996373516 cites W2963185411 @default.
• W2996373516 cites W2964186773 @default.
• W2996373516 cites W3098221464 @default.
• W2996373516 cites W3098724574 @default.
• W2996373516 cites W3101109224 @default.
• W2996373516 cites W3105225363 @default.
• W2996373516 cites W3105494006 @default.
• W2996373516 cites W3106305664 @default.
• W2996373516 doi "https://doi.org/10.1186/s40668-019-0032-1" @default.
• W2996373516 hasPublicationYear "2019" @default.
• W2996373516 type Work @default.
• W2996373516 sameAs 2996373516 @default.
• W2996373516 citedByCount "19" @default.
• W2996373516 countsByYear W29963735162019 @default.
• W2996373516 countsByYear W29963735162020 @default.
• W2996373516 countsByYear W29963735162021 @default.
• W2996373516 countsByYear W29963735162022 @default.
• W2996373516 countsByYear W29963735162023 @default.
• W2996373516 crossrefType "journal-article" @default.
• W2996373516 hasAuthorship W2996373516A5018692490 @default.
• W2996373516 hasAuthorship W2996373516A5026330747 @default.
• W2996373516 hasAuthorship W2996373516A5045413165 @default.
• W2996373516 hasAuthorship W2996373516A5059632472 @default.
• W2996373516 hasAuthorship W2996373516A5060064717 @default.
• W2996373516 hasAuthorship W2996373516A5068049945 @default.
• W2996373516 hasBestOaLocation W29963735161 @default.
• W2996373516 hasConcept C108583219 @default.
• W2996373516 hasConcept C111919701 @default.
• W2996373516 hasConcept C119857082 @default.
• W2996373516 hasConcept C121332964 @default.
• W2996373516 hasConcept C13280743 @default.
• W2996373516 hasConcept C154945302 @default.
• W2996373516 hasConcept C163258240 @default.
• W2996373516 hasConcept C167966045 @default.
• W2996373516 hasConcept C185798385 @default.
• W2996373516 hasConcept C205649164 @default.
• W2996373516 hasConcept C26405456 @default.
• W2996373516 hasConcept C26517878 @default.
• W2996373516 hasConcept C2780992000 @default.
• W2996373516 hasConcept C38652104 @default.
• W2996373516 hasConcept C39890363 @default.
• W2996373516 hasConcept C41008148 @default.
• W2996373516 hasConcept C48044578 @default.
• W2996373516 hasConcept C62520636 @default.
• W2996373516 hasConcept C77088390 @default.
• W2996373516 hasConcept C98045186 @default.
• W2996373516 hasConceptScore W2996373516C108583219 @default.
• W2996373516 hasConceptScore W2996373516C111919701 @default.
• W2996373516 hasConceptScore W2996373516C119857082 @default.
• W2996373516 hasConceptScore W2996373516C121332964 @default.
• W2996373516 hasConceptScore W2996373516C13280743 @default.
• W2996373516 hasConceptScore W2996373516C154945302 @default.
• W2996373516 hasConceptScore W2996373516C163258240 @default.
• W2996373516 hasConceptScore W2996373516C167966045 @default.
• W2996373516 hasConceptScore W2996373516C185798385 @default.
• W2996373516 hasConceptScore W2996373516C205649164 @default.
• W2996373516 hasConceptScore W2996373516C26405456 @default.
• W2996373516 hasConceptScore W2996373516C26517878 @default.
• W2996373516 hasConceptScore W2996373516C2780992000 @default.
• W2996373516 hasConceptScore W2996373516C38652104 @default.
• W2996373516 hasConceptScore W2996373516C39890363 @default.
• W2996373516 hasConceptScore W2996373516C41008148 @default.
• W2996373516 hasConceptScore W2996373516C48044578 @default.
• W2996373516 hasConceptScore W2996373516C62520636 @default.
• W2996373516 hasConceptScore W2996373516C77088390 @default.

• next