Machine-Learning Dessins d'Enfants: Explorations via Modular and Seiberg-Witten Curves

We apply machine-learning to the study of dessins d'enfants. Specifically, we investigate a class of dessins which reside at the intersection of the investigations of modular subgroups, Seiberg-Witten curves and extremal elliptic K3 surfaces. A deep feed-forward neural network with simple structure and standard activation functions without prior knowledge of the underlying mathematics is established and imposed onto the classification of extension degree over the rationals, known to be a difficult problem. The classifications exceeded 0.93 accuracy and around 0.9 confidence relatively quickly. The Seiberg-Witten curves for those with rational coefficients are also tabulated.

[1]  Yang-Hui He,et al.  Dessins d’enfants in N=2$$ \mathcal{N}=2 $$ generalised quiver theories , 2015, 1503.06418.

[2]  R. Vidunas,et al.  Genus one Belyi maps by quadratic correspondences , 2017, International Journal of Mathematics.

[3]  R. Debuchy,et al.  What is a , 1997 .

[4]  Nikhil Buduma,et al.  Fundamentals of deep learning , 2017 .

[5]  Vishnu Jejjala,et al.  INVARIANTS OF TORIC SEIBERG DUALITY , 2011, 1107.4101.

[6]  Fabian Ruehle.  Data science applications to string theory , 2020 .

[7]  Michele Banko,et al.  Mitigating the Paucity-of-Data Problem: Exploring the Effect of Training Corpus Size on Classifier Performance for Natural Language Processing , 2001, HLT.

[8]  Yang-Hui He,et al.  N=2 gauge theories: Congruence subgroups, coset graphs, and modular surfaces , 2012, 1201.3633.

[9]  Fabian Ruehle.  Evolving neural networks with genetic algorithms to study the string landscape , 2017, 1706.07024.

[10]  Andrea Baronchelli,et al.  Machine Learning meets Number Theory: The Data Science of Birch-Swinnerton-Dyer , 2019, ArXiv.

[11]  Sabri Boughorbel,et al.  Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric , 2017, PloS one.

[12]  Y. Kimura.  Nongeometric heterotic strings and dual F-theory with enhanced gauge groups , 2018, Journal of High Energy Physics.

[13]  Vishnu Jejjala,et al.  Toric CFTs, permutation triples, and Belyi pairs , 2010, 1012.2351.

[14]  Chen Sun,et al.  Revisiting Unreasonable Effectiveness of Data in Deep Learning Era , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  志村 五郎,et al.  Introduction to the arithmetic theory of automorphic functions , 1971 .

[16]  Vishnu Jejjala,et al.  The beta ansatz: a tale of two complex structures , 2011, 1104.5490.

[17]  Burt A. Ovrut,et al.  Machine Learning Calabi–Yau Metrics , 2019 .

[18]  F. Klein.  Ueber die Transformation elfter Ordnung der elliptischen Functionen , 1879 .

[19]  Modular subgroups, dessins d’enfants and elliptic K3 surfaces , 2012, 1211.1931.

[20]  Ulf Persson,et al.  Configurations of In fibers on elliptic K 3 surfaces , 1989 .

[21]  D. Krefl,et al.  Machine Learning of Calabi-Yau Volumes : arXiv , 2017, 1706.03346.

[22]  Yang-Hui He,et al.  Machine-learning the string landscape , 2017 .

[23]  Zhi Hu,et al.  Yang-Mills Theory and the ABC Conjecture , 2016, 1602.01780.

[24]  Gauge symmetries and matter fields in $\mathrm{F}$-theory models without section — compactifications on double cover and Fermat quartic $\mathrm{K}3$ constructions times $\mathrm{K}3$ , 2016, 1603.03212.

[25]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[26]  N. Seiberg,et al.  Electric - magnetic duality, monopole condensation, and confinement in N=2 supersymmetric Yang-Mills theory , 1994 .

[27]  Gauge theories from toric geometry and brane tilings , 2005, hep-th/0505211.

[28]  Children’s drawings from Seiberg–Witten curves , 2006, hep-th/0611082.

[29]  Yang-Hui He,et al.  The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning , 2018, 1812.02893.

[30]  William H. Offenhauser,et al.  Wild Boars as Hosts of Human-Pathogenic Anaplasma phagocytophilum Variants , 2012, Emerging infectious diseases.

[31]  Jean-Pierre Chauveau,et al.  Esquisse d'un programme , 1982 .

[32]  Yuji Tachikawa.  N=2 Supersymmetric Dynamics for Pedestrians , 2013, 1312.2684.

[33]  Callum R. Brodie,et al.  Machine Learning Line Bundle Cohomology , 2019, Fortschritte der Physik.

[34]  F. Beukers,et al.  Number Theory and Polynomials: Explicit calculation of elliptic fibrations of K 3-surfaces and their Belyi-maps , 2008 .

[35]  A. Sebbar.  Classification of torsion-free genus zero congruence groups , 2001 .