FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306174017> ?p ?o ?g. }

• W4306174017 endingPage "101955" @default.
• W4306174017 startingPage "101955" @default.
• W4306174017 abstract "A great challenge of cosmology is estimating the cosmological parameters of the universe. With the development of deep learning, scientists adopt 3D deep neural networks to estimate cosmological parameters from the large-scale dark matter distribution of the universe, but these methods are time-consuming to design and train neural networks. While neural architecture search is an emerging approach to estimate cosmological parameters with its capability of automatically designing neural networks, the 3D operations on a 3D dataset prohibit the usage of traditional neural architecture search methods, due to its overwhelming time and memory consumption. To tackle these issues, we propose an efficient method, CosNAS, that can automatically design neural networks with 2D operations to estimate the cosmological parameters. In addition, processing 3D data with 2D operations will inevitably cause the loss of spatial information, thus we propose an efficient SABlock to retain more 3D spatial information. We also customize a space-focused search space to focus on important information in the dark matter distribution. The experimental results indicate that our estimation of the cosmological parameters Ω , σ and n , can be applied to large-scale 3D dark matter distribution and speedup the network search by 800x. The average relative errors of cosmological parameter estimations are (0.00163, 0.00065, 0.00080), significantly decreasing the average error of estimation by 85.5% compared to previous work. • Our work is the first attempt to extend NAS to predict the universal parameters from the dark matter distribution in the domain of cosmology. We propose CosNAS to process large-scale 3D dark matter distribution and predict the cosmological parameters Ω , sigma and n, achieving state-of-the-art performance with only 4 GPU days. • We are the first to use 2D operator operations instead of the previous 3D convolution operations for 3D dark matter distribution data. To reserve spatial information as much as possible in our CosNAS, we put forward a complement module called SABlock. • We propose a space-focused search space (SFSS) for capturing features in the distribution of dark matter more efficiently, improving the predictive accuracy of cosmological parameters." @default.
• W4306174017 created "2022-10-14" @default.
• W4306174017 creator A5022047446 @default.
• W4306174017 creator A5023539493 @default.
• W4306174017 creator A5024085713 @default.
• W4306174017 creator A5057221447 @default.
• W4306174017 creator A5072037382 @default.
• W4306174017 creator A5076345724 @default.
• W4306174017 date "2023-02-01" @default.
• W4306174017 modified "2023-10-04" @default.
• W4306174017 title "CosNAS: Enhancing estimation on cosmological parameters via neural architecture search" @default.
• W4306174017 cites W1689711448 @default.
• W4306174017 cites W1853767801 @default.
• W4306174017 cites W2005013882 @default.
• W4306174017 cites W2036439761 @default.
• W4306174017 cites W2071433262 @default.
• W4306174017 cites W2073832139 @default.
• W4306174017 cites W2095266808 @default.
• W4306174017 cites W2128759530 @default.
• W4306174017 cites W2143513913 @default.
• W4306174017 cites W2153305744 @default.
• W4306174017 cites W2773706593 @default.
• W4306174017 cites W2886189612 @default.
• W4306174017 cites W2963136578 @default.
• W4306174017 cites W2963420686 @default.
• W4306174017 cites W2964081807 @default.
• W4306174017 cites W2965658867 @default.
• W4306174017 cites W2981748264 @default.
• W4306174017 cites W3034535818 @default.
• W4306174017 cites W3090728869 @default.
• W4306174017 cites W3098724574 @default.
• W4306174017 cites W3125864581 @default.
• W4306174017 doi "https://doi.org/10.1016/j.newast.2022.101955" @default.
• W4306174017 hasPublicationYear "2023" @default.
• W4306174017 type Work @default.
• W4306174017 citedByCount "0" @default.
• W4306174017 crossrefType "journal-article" @default.
• W4306174017 hasAuthorship W4306174017A5022047446 @default.
• W4306174017 hasAuthorship W4306174017A5023539493 @default.
• W4306174017 hasAuthorship W4306174017A5024085713 @default.
• W4306174017 hasAuthorship W4306174017A5057221447 @default.
• W4306174017 hasAuthorship W4306174017A5072037382 @default.
• W4306174017 hasAuthorship W4306174017A5076345724 @default.
• W4306174017 hasConcept C119857082 @default.
• W4306174017 hasConcept C121332964 @default.
• W4306174017 hasConcept C123657996 @default.
• W4306174017 hasConcept C142362112 @default.
• W4306174017 hasConcept C153349607 @default.
• W4306174017 hasConcept C26405456 @default.
• W4306174017 hasConcept C2992891135 @default.
• W4306174017 hasConcept C41008148 @default.
• W4306174017 hasConcept C44870925 @default.
• W4306174017 hasConcept C50644808 @default.
• W4306174017 hasConceptScore W4306174017C119857082 @default.
• W4306174017 hasConceptScore W4306174017C121332964 @default.
• W4306174017 hasConceptScore W4306174017C123657996 @default.
• W4306174017 hasConceptScore W4306174017C142362112 @default.
• W4306174017 hasConceptScore W4306174017C153349607 @default.
• W4306174017 hasConceptScore W4306174017C26405456 @default.
• W4306174017 hasConceptScore W4306174017C2992891135 @default.
• W4306174017 hasConceptScore W4306174017C41008148 @default.
• W4306174017 hasConceptScore W4306174017C44870925 @default.
• W4306174017 hasConceptScore W4306174017C50644808 @default.
• W4306174017 hasLocation W43061740171 @default.
• W4306174017 hasOpenAccess W4306174017 @default.
• W4306174017 hasPrimaryLocation W43061740171 @default.
• W4306174017 hasRelatedWork W2008086601 @default.
• W4306174017 hasRelatedWork W2010133960 @default.
• W4306174017 hasRelatedWork W2163686557 @default.
• W4306174017 hasRelatedWork W3098665537 @default.
• W4306174017 hasRelatedWork W3098791626 @default.
• W4306174017 hasRelatedWork W3099673353 @default.
• W4306174017 hasRelatedWork W3103114574 @default.
• W4306174017 hasRelatedWork W3104117543 @default.
• W4306174017 hasRelatedWork W3145073591 @default.
• W4306174017 hasRelatedWork W622982746 @default.
• W4306174017 hasVolume "99" @default.
• W4306174017 isParatext "false" @default.
• W4306174017 isRetracted "false" @default.
• W4306174017 workType "article" @default.