Getting CICY high

被引：30

作者：

Bull, Kieran ^{[1
,2
]}

He, Yang-Hui ^{[2
,3
,4
,5
]}

Jejjala, Vishnu ^{[6
,7
,8
]}

Mishra, Challenger ^{[9
,10
,11
]}

机构：

[1] Univ Leeds, Sch Phys & Astron, Leeds LS2 9JT, W Yorkshire, England

[2] Univ Oxford, Clarendon Lab, Rudolf Peierls Ctr Theoret Phys, Parks Rd, Oxford OX1 3PU, England

[3] City Univ London, Dept Math, London, England

[4] Univ Oxford, Merton Coll, Oxford, England

[5] Nankai Univ, Sch Phys, Tianjin, Peoples R China

[6] Univ Witwatersrand, CoE MaSS, NITheP, Mandelstam Inst Theoret Phys, Johannesburg, South Africa

[7] Univ Witwatersrand, Sch Phys, Johannesburg, South Africa

[8] Univ Penn, David Rittenhouse Lab, Philadelphia, PA 19104 USA

[9] Alan Turing Inst, London, England

[10] Univ Oxford, Dept Comp Sci, Oxford, England

[11] ICMAT, Inst Ciencias Matemat, Madrid, Spain

来源：

PHYSICS LETTERS B | 2019年 / 795卷

基金：

英国科学技术设施理事会;

关键词：

Machine learning; Neural network; Support Vector Machine; Calabi-Yau; String compactifications; CALABI-YAU MANIFOLDS;

D O I：

10.1016/j.physletb.2019.06.067

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

Supervised machine learning can be used to predict properties of string geometries with previously unknown features. Using the complete intersection Calabi-Yau (CICY) threefold dataset as a theoretical laboratory for this investigation, we use low h(1,1) geometries for training and validate on geometries with large h(1,1). Neural networks and Support Vector Machines successfully predict trends in the number of Kohler parameters of CICY threefolds. The numerical accuracy of machine learning improves upon seeding the training set with a small number of samples at higher h(1,1). (C) 2019 The Authors. Published by Elsevier B.V.

引用

页码：700 / 706

页数：7

共 53 条

[1] Genetic algorithms and the search for viable string vacua [J].