English
Related papers

Related papers: Inception Neural Network for Complete Intersection…

200 papers

We consider the construction of Calabi-Yau varieties recently generalized to where the defining equations may have negative degrees over some projective space factors in the embedding space. Within such "generalized complete intersection"…

High Energy Physics - Theory · Physics 2020-01-07 Per Berglund , Tristan Hubsch

In these lecture notes, we survey the landscape of Calabi-Yau threefolds, and the use of machine learning to explore it. We begin with the compact portion of the landscape, focusing in particular on complete intersection Calabi-Yau…

High Energy Physics - Theory · Physics 2020-02-05 Jiakang Bao , Yang-Hui He , Edward Hirst , Stephen Pietromonaco

We investigate the mathematical properties of the class of Calabi-Yau four-folds recently found in [arXiv:1303.1832]. This class consists of 921,497 configuration matrices which correspond to manifolds that are described as complete…

High Energy Physics - Theory · Physics 2014-09-19 James Gray , Alexander S. Haupt , Andre Lukas

Deep convolutional neural networks (DCNNs) are an influential tool for solving various problems in the machine learning and computer vision fields. In this paper, we introduce a new deep learning model called an Inception- Recurrent…

Computer Vision and Pattern Recognition · Computer Science 2017-04-26 Md Zahangir Alom , Mahmudul Hasan , Chris Yakopcic , Tarek M. Taha

We present a novel way to classify Calabi-Yau threefolds by systematically studying their infinite volume limits. Each such limit is at infinite distance in Kahler moduli space and can be classified by an associated limiting mixed Hodge…

High Energy Physics - Theory · Physics 2021-12-21 Thomas W. Grimm , Fabian Ruehle , Damian van de Heisteeg

We propose machine learning inspired methods for computing numerical Calabi-Yau (Ricci flat K\"ahler) metrics, and implement them using Tensorflow/Keras. We compare them with previous work, and find that they are far more accurate for…

High Energy Physics - Theory · Physics 2021-05-06 Michael R. Douglas , Subramanian Lakshminarasimhan , Yidi Qi

Finding Ricci-flat (Calabi-Yau) metrics is a long standing problem in geometry with deep implications for string theory and phenomenology. A new attack on this problem uses neural networks to engineer approximations to the Calabi-Yau metric…

High Energy Physics - Theory · Physics 2024-06-10 Per Berglund , Giorgi Butbaia , Tristan Hübsch , Vishnu Jejjala , Damián Mayorga Peña , Challenger Mishra , Justin Tan

We study nodal complete intersection threefolds of type $(2,4)$ in $\PP^5$ which contain an Enriques surface in its Fano embedding. We completely determine Calabi-Yau birational models of a generic such threefold. These models have Hodge…

Algebraic Geometry · Mathematics 2016-06-15 Lev A. Borisov , Howard J. Nuer

We test the possibility of using a convolutional neural network to infer the inclination angle of a black hole directly from the incomplete image of the black hole's shadow in the $uv$-plane. To this end, we develop a proof-of-concept…

High Energy Astrophysical Phenomena · Physics 2023-11-29 Anton A. Popov , Vladimir Strokov , Aleksey A. Surdyaev

A numerical framework for approximating $\mathrm{G}_2$-structure 3-forms on contact Calabi-Yau manifolds is presented. The approach proceeds in three stages: first, existing neural network models are employed to compute an approximate…

Differential Geometry · Mathematics 2026-02-16 Elli Heyes , Edward Hirst , Henrique N. Sá Earp , Tomás S. R. Silva

We extend previous computations of Calabi-Yau metrics on projective hypersurfaces to free quotients, complete intersections, and free quotients of complete intersections. In particular, we construct these metrics on generic quintics,…

High Energy Physics - Theory · Physics 2015-03-13 Volker Braun , Tamaz Brelidze , Michael R. Douglas , Burt A. Ovrut

Identifying symmetries in data sets is generally difficult, but knowledge about them is crucial for efficient data handling. Here we present a method how neural networks can be used to identify symmetries. We make extensive use of the…

Computational Physics · Physics 2020-03-31 Sven Krippendorf , Marc Syvaeri

Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task performance but little transparency. Prior work has explored hybrid formulations that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Tores Julie , Sun Rémy , Sassatelli Lucile , Ancarani Elisa , Wu Hui-Yin , Precioso Frédéric

We present new invariant machine learning models that approximate the Ricci-flat metric on Calabi-Yau (CY) manifolds with discrete symmetries. We accomplish this by combining the $\phi$-model of the cymetric package with non-trainable,…

High Energy Physics - Theory · Physics 2024-09-13 Yacoub Hendi , Magdalena Larfors , Moritz Walden

Initial weighting is significant in deep neural networks because the random selection of weights produces different outputs and increases the probability of overfitting and underfitting. On the other hand, vector-based approaches to extract…

Image and Video Processing · Electrical Eng. & Systems 2024-02-07 Elham Sadeghnezhad , Sajjad Salem

Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has been addressed by the various compositions of subset…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Jihwan Park , SeungJun Lee , Hwan Heo , Hyeong Kyu Choi , Hyunwoo J. Kim

This paper proposes a Deep Learning based edge detector, which is inspired on both HED (Holistically-Nested Edge Detection) and Xception networks. The proposed approach generates thin edge-maps that are plausible for human eyes; it can be…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Xavier Soria , Edgar Riba , Angel D. Sappa

We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,lines, circles, and B-splines). Accordingly, our deep neural…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Xiaogang Wang , Yuelang Xu , Kai Xu , Andrea Tagliasacchi , Bin Zhou , Ali Mahdavi-Amiri , Hao Zhang

We present a list of Calabi-Yau threefolds known to us, and with holonomy groups that are precisely SU(3), rather than a subgroup, with small Hodge numbers, which we understand to be those manifolds with height $(h^{1,1}+h^{2,1})\le 24$.…

High Energy Physics - Theory · Physics 2018-07-06 Philip Candelas , Andrei Constantin , Challenger Mishra

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a…

Computer Vision and Pattern Recognition · Computer Science 2017-04-06 François Chollet