FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046248316> ?p ?o ?g. }

• W3046248316 abstract "We revisit the question of predicting both Hodge numbers $h^{1,1}$ and $h^{2,1}$ of complete intersection Calabi-Yau (CICY) 3-folds using machine learning (ML), considering both the old and new datasets built respectively by Candelas-Dale-Lutken-Schimmrigk / Green-Hubsch-Lutken and by Anderson-Gao-Gray-Lee. In real world applications, implementing a ML system rarely reduces to feed the brute data to the algorithm. Instead, the typical workflow starts with an exploratory data analysis (EDA) which aims at understanding better the input data and finding an optimal representation. It is followed by the design of a validation procedure and a baseline model. Finally, several ML models are compared and combined, often involving neural networks with a topology more complicated than the sequential models typically used in physics. By following this procedure, we improve the accuracy of ML computations for Hodge numbers with respect to the existing literature. First, we obtain 97% (resp. 99%) accuracy for $h^{1,1}$ using a neural network inspired by the Inception model for the old dataset, using only 30% (resp. 70%) of the data for training. For the new one, a simple linear regression leads to almost 100% accuracy with 30% of the data for training. The computation of $h^{2,1}$ is less successful as we manage to reach only 50% accuracy for both datasets, but this is still better than the 16% obtained with a simple neural network (SVM with Gaussian kernel and feature engineering and sequential convolutional network reach at best 36%). This serves as a proof of concept that neural networks can be valuable to study the properties of geometries appearing in string theory." @default.
• W3046248316 created "2020-08-07" @default.
• W3046248316 creator A5041490002 @default.
• W3046248316 creator A5052904094 @default.
• W3046248316 date "2021-06-15" @default.
• W3046248316 modified "2023-10-14" @default.
• W3046248316 title "Machine learning for complete intersection Calabi-Yau manifolds: A methodological study" @default.
• W3046248316 cites W1491547817 @default.
• W3046248316 cites W1498436455 @default.
• W3046248316 cites W1678356000 @default.
• W3046248316 cites W1923361784 @default.
• W3046248316 cites W1939025161 @default.
• W3046248316 cites W1985092508 @default.
• W3046248316 cites W1996475841 @default.
• W3046248316 cites W1997683411 @default.
• W3046248316 cites W2011301426 @default.
• W3046248316 cites W2028949988 @default.
• W3046248316 cites W2035026703 @default.
• W3046248316 cites W2060149048 @default.
• W3046248316 cites W2065762817 @default.
• W3046248316 cites W2070493638 @default.
• W3046248316 cites W2086439453 @default.
• W3046248316 cites W2103054632 @default.
• W3046248316 cites W2162232298 @default.
• W3046248316 cites W2163104504 @default.
• W3046248316 cites W2178552379 @default.
• W3046248316 cites W2192203593 @default.
• W3046248316 cites W2261689926 @default.
• W3046248316 cites W2558748708 @default.
• W3046248316 cites W2614895328 @default.
• W3046248316 cites W2622312016 @default.
• W3046248316 cites W2626828082 @default.
• W3046248316 cites W2728819519 @default.
• W3046248316 cites W2766409877 @default.
• W3046248316 cites W2766422261 @default.
• W3046248316 cites W2787049258 @default.
• W3046248316 cites W2788808196 @default.
• W3046248316 cites W2806878911 @default.
• W3046248316 cites W2889983866 @default.
• W3046248316 cites W2890041438 @default.
• W3046248316 cites W2891834385 @default.
• W3046248316 cites W2892666903 @default.
• W3046248316 cites W2893538824 @default.
• W3046248316 cites W2900843847 @default.
• W3046248316 cites W2901947642 @default.
• W3046248316 cites W2904411115 @default.
• W3046248316 cites W2913340405 @default.
• W3046248316 cites W2922301641 @default.
• W3046248316 cites W2923537029 @default.
• W3046248316 cites W2925283579 @default.
• W3046248316 cites W2940343590 @default.
• W3046248316 cites W2960999379 @default.
• W3046248316 cites W2963800692 @default.
• W3046248316 cites W2964025189 @default.
• W3046248316 cites W2976550984 @default.
• W3046248316 cites W2982468996 @default.
• W3046248316 cites W2982581276 @default.
• W3046248316 cites W2990783773 @default.
• W3046248316 cites W2991376628 @default.
• W3046248316 cites W2997692532 @default.
• W3046248316 cites W3010157268 @default.
• W3046248316 cites W3011698838 @default.
• W3046248316 cites W3014053398 @default.
• W3046248316 cites W3018080999 @default.
• W3046248316 cites W3021569528 @default.
• W3046248316 cites W3022477152 @default.
• W3046248316 cites W3045303605 @default.
• W3046248316 cites W3048796016 @default.
• W3046248316 cites W3080882611 @default.
• W3046248316 cites W3086664930 @default.
• W3046248316 cites W3098142336 @default.
• W3046248316 cites W3098279998 @default.
• W3046248316 cites W3099142111 @default.
• W3046248316 cites W3099185239 @default.
• W3046248316 cites W3099306974 @default.
• W3046248316 cites W3100056294 @default.
• W3046248316 cites W3101526912 @default.
• W3046248316 cites W3102158583 @default.
• W3046248316 cites W3103282954 @default.
• W3046248316 cites W3103722330 @default.
• W3046248316 cites W3104240813 @default.
• W3046248316 cites W3105570377 @default.
• W3046248316 cites W3105799564 @default.
• W3046248316 cites W3105927042 @default.
• W3046248316 cites W3106019322 @default.
• W3046248316 cites W3122525396 @default.
• W3046248316 cites W3125303534 @default.
• W3046248316 cites W4236137412 @default.
• W3046248316 cites W4239510810 @default.
• W3046248316 cites W4294588935 @default.
• W3046248316 cites W3037032868 @default.
• W3046248316 doi "https://doi.org/10.1103/physrevd.103.126014" @default.
• W3046248316 hasPublicationYear "2021" @default.
• W3046248316 type Work @default.
• W3046248316 sameAs 3046248316 @default.
• W3046248316 citedByCount "14" @default.
• W3046248316 countsByYear W30462483162018 @default.
• W3046248316 countsByYear W30462483162020 @default.
• W3046248316 countsByYear W30462483162021 @default.
• W3046248316 countsByYear W30462483162022 @default.

• next