Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090728869> ?p ?o ?g. }
- W3090728869 abstract "We propose a light-weight deep convolutional neural network (CNN) to estimate the cosmological parameters from simulated 3-dimensional dark matter distributions with high accuracy. The training set is based on 465 realizations of a cubic box with a side length of 256 h−1 Mpc, sampled with 1283 particles interpolated over a cubic grid of 1283 voxels. These volumes have cosmological parameters varying within the flat ΛCDM parameter space of 0.16 ≤ Ωm ≤ 0.46 and 2.0 ≤ 109As ≤ 2.3. The neural network takes as an input cubes with 323 voxels and has three convolution layers, three dense layers, together with some batch normalization and pooling layers. In the final predictions from the network we find a 2.5% bias on the primordial amplitude σ8 that cannot easily be resolved by continued training. We correct this bias to obtain unprecedented accuracy in the cosmological parameter estimation with statistical uncertainties of δΩm=0.0015 and δσ8=0.0029, which are several times better than the results of previous CNN works. Compared with a 2-point analysis method using the clustering region of 0–130 and 10–130 h−1 Mpc, the CNN constraints are several times and an order of magnitude more precise, respectively. Finally, we conduct preliminary checks of the error-tolerance abilities of the neural network, and find that it exhibits robustness against smoothing, masking, random noise, global variation, rotation, reflection, and simulation resolution. Those effects are well understood in typical clustering analysis, but had not been tested before for the CNN approach. Our work shows that CNN can be more promising than people expected in deriving tight cosmological constraints from the cosmic large scale structure." @default.
- W3090728869 created "2020-10-08" @default.
- W3090728869 creator A5001954997 @default.
- W3090728869 creator A5011132586 @default.
- W3090728869 creator A5011914679 @default.
- W3090728869 creator A5020763235 @default.
- W3090728869 creator A5029115319 @default.
- W3090728869 creator A5070965127 @default.
- W3090728869 creator A5075567505 @default.
- W3090728869 date "2020-09-11" @default.
- W3090728869 modified "2023-10-06" @default.
- W3090728869 title "Cosmological parameter estimation from large-scale structure deep learning" @default.
- W3090728869 cites W1520258040 @default.
- W3090728869 cites W1853767801 @default.
- W3090728869 cites W1894431533 @default.
- W3090728869 cites W1913081498 @default.
- W3090728869 cites W1975088809 @default.
- W3090728869 cites W1989589910 @default.
- W3090728869 cites W1999367759 @default.
- W3090728869 cites W2005013882 @default.
- W3090728869 cites W2018192802 @default.
- W3090728869 cites W2021620550 @default.
- W3090728869 cites W2026711574 @default.
- W3090728869 cites W2036439761 @default.
- W3090728869 cites W2048021339 @default.
- W3090728869 cites W2048877765 @default.
- W3090728869 cites W2051694884 @default.
- W3090728869 cites W2055327934 @default.
- W3090728869 cites W2056173066 @default.
- W3090728869 cites W2065889919 @default.
- W3090728869 cites W2071433262 @default.
- W3090728869 cites W2073603601 @default.
- W3090728869 cites W2073619438 @default.
- W3090728869 cites W2073832139 @default.
- W3090728869 cites W2090794178 @default.
- W3090728869 cites W2102336972 @default.
- W3090728869 cites W2114310261 @default.
- W3090728869 cites W2121951791 @default.
- W3090728869 cites W2128759530 @default.
- W3090728869 cites W2139900404 @default.
- W3090728869 cites W2142955287 @default.
- W3090728869 cites W2153305744 @default.
- W3090728869 cites W2156305595 @default.
- W3090728869 cites W2157917411 @default.
- W3090728869 cites W2162231850 @default.
- W3090728869 cites W2170967203 @default.
- W3090728869 cites W2283612628 @default.
- W3090728869 cites W2292579160 @default.
- W3090728869 cites W2437571239 @default.
- W3090728869 cites W2461007441 @default.
- W3090728869 cites W2464001455 @default.
- W3090728869 cites W2501306320 @default.
- W3090728869 cites W2501864044 @default.
- W3090728869 cites W2755803331 @default.
- W3090728869 cites W2787427854 @default.
- W3090728869 cites W2787443430 @default.
- W3090728869 cites W2794365114 @default.
- W3090728869 cites W2795639206 @default.
- W3090728869 cites W2797258416 @default.
- W3090728869 cites W2799470320 @default.
- W3090728869 cites W2890104560 @default.
- W3090728869 cites W2898187790 @default.
- W3090728869 cites W2898457303 @default.
- W3090728869 cites W2898595154 @default.
- W3090728869 cites W2900466252 @default.
- W3090728869 cites W2901812353 @default.
- W3090728869 cites W2902970406 @default.
- W3090728869 cites W2923557884 @default.
- W3090728869 cites W2940261095 @default.
- W3090728869 cites W2942776032 @default.
- W3090728869 cites W2945962475 @default.
- W3090728869 cites W2949142645 @default.
- W3090728869 cites W2959589769 @default.
- W3090728869 cites W2963079905 @default.
- W3090728869 cites W2963241626 @default.
- W3090728869 cites W2971425070 @default.
- W3090728869 cites W3037504478 @default.
- W3090728869 cites W3099582894 @default.
- W3090728869 cites W3100272886 @default.
- W3090728869 cites W3103494697 @default.
- W3090728869 cites W3103722330 @default.
- W3090728869 cites W3104332386 @default.
- W3090728869 cites W3104465300 @default.
- W3090728869 cites W3104489948 @default.
- W3090728869 cites W3104858412 @default.
- W3090728869 cites W3105214921 @default.
- W3090728869 cites W3105348217 @default.
- W3090728869 cites W3105494006 @default.
- W3090728869 cites W3105945550 @default.
- W3090728869 cites W3122149089 @default.
- W3090728869 cites W4237064514 @default.
- W3090728869 cites W4288948729 @default.
- W3090728869 cites W4289916580 @default.
- W3090728869 cites W3098868183 @default.
- W3090728869 doi "https://doi.org/10.1007/s11433-020-1586-3" @default.
- W3090728869 hasPublicationYear "2020" @default.
- W3090728869 type Work @default.
- W3090728869 sameAs 3090728869 @default.
- W3090728869 citedByCount "15" @default.
- W3090728869 countsByYear W30907288692020 @default.