Corpus ID: 235266045

Planck Limits on Cosmic String Tension Using Machine Learning

  title={Planck Limits on Cosmic String Tension Using Machine Learning},
  author={Maryam Torki and H. Hajizadeh and Marzieh Farhang and Alireza Vafaei Sadr and S. M. S. Movahed},
We develop two parallel machine-learning pipelines to estimate the contribution of cosmic strings (CSs), conveniently encoded in their tension (Gμ), to the anisotropies of the cosmic microwave background radiation observed by Planck. The first approach is tree-based and feeds on certain map features derived by image processing and statistical tools. The second uses convolutional neural network with the goal to explore possible non-trivial features of the CS imprints. The two pipelines are… Expand

Figures and Tables from this paper


Dark Matter Distribution Induced by a Cosmic String Wake in the Nonlinear Regime
We study the distribution of dark matter in the nonlinear regime in a model in which the primordial fluctuations include, in addition to the dominant primordial Gaussian fluctuations generated by theExpand
Cosmic Strings and Other Topological Defects
Preface 1. Introduction 2. Phase transitions in the early universe 3. Topological defects 4. String field theory 5. Superconducting strings 6. String dynamics 7. String gravity 8. String interactionsExpand
Fundamentals of Artificial Neural Networks
  • M. Hassoun
  • Computer Science
  • Proceedings of the IEEE
  • 1996
Fundamentals of Artificial Neural Networks provides the first systematic account of artificial neural network paradigms by identifying clearly the fundamental concepts and major methodologies underlying most of the current theory and practice employed by neural network researchers. Expand
Artificial Neural Networks
  • A. Roli
  • Mathematics
  • Lecture Notes in Computer Science
  • 1995
Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminologyExpand
Automatic computation of surface correspondence via harmonic map is an active research field in computer vision, computer graphics and computational geometry. It may help document and understandExpand
Curvelets: A Surprisingly Effective Nonadaptive Representation for Objects with Edges
Abstract : It is widely believed that to efficiently represent an otherwise smooth object with discontinuities along edges, one must use an adaptive representation that in some sense 'tracks' theExpand
2016, in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining
  • 2016
Fundamentals of artificial neural networks. MIT press
  • 1995
2016, in 12th {USENIX} symposium on
  • 2016
Deep Learning