Artificial neural network in cosmic landscape

Liu, Junyu

doi:10.1007/jhep12(2017)149

Title: Artificial neural network in cosmic landscape

Abstract

In this study we propose that artificial neural network, the basis of machine learning, is useful to generate the inflationary landscape from a cosmological point of view. Traditional numerical simulations of a global cosmic landscape typically need an exponential complexity when the number of fields is large. However, a basic application of artificial neural network could solve the problem based on the universal approximation theorem of the multilayer perceptron. A toy model in inflation with multiple light fields is investigated numerically as an example of such an application.

Authors:

Liu, Junyu ^[1]

California Inst. of Technology (CalTech), Pasadena, CA (United States)

Publication Date:: Thu Dec 28 00:00:00 EST 2017

Research Org.:: California Institute of Technology (CalTech), Pasadena, CA (United States)

Sponsoring Org.:: USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:: 1501472

Grant/Contract Number:: SC0011632

Resource Type:: Accepted Manuscript

Journal Name:: Journal of High Energy Physics (Online)

Additional Journal Information:: Journal Name: Journal of High Energy Physics (Online); Journal Volume: 2017; Journal Issue: 12; Journal ID: ISSN 1029-8479

Publisher:: Springer Berlin

Country of Publication:: United States

Language:: English

Subject:: 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; 79 ASTRONOMY AND ASTROPHYSICS; Cosmology of Theories beyond the SM; Models of Quantum Gravity; Random Systems

Citation Formats


                    Liu, Junyu. Artificial neural network in cosmic landscape.  United States: N. p., 2017. 
Web.  doi:10.1007/jhep12(2017)149.

Copy to clipboard


                    Liu, Junyu. Artificial neural network in cosmic landscape.  United States.  https://doi.org/10.1007/jhep12(2017)149

Copy to clipboard


                    Liu, Junyu. Thu .  
"Artificial neural network in cosmic landscape".  United States.  https://doi.org/10.1007/jhep12(2017)149.  https://www.osti.gov/servlets/purl/1501472.

Copy to clipboard


                    
@article{osti_1501472,

  title        = {Artificial neural network in cosmic landscape},

  author       = {Liu, Junyu},

  abstractNote = {In this study we propose that artificial neural network, the basis of machine learning, is useful to generate the inflationary landscape from a cosmological point of view. Traditional numerical simulations of a global cosmic landscape typically need an exponential complexity when the number of fields is large. However, a basic application of artificial neural network could solve the problem based on the universal approximation theorem of the multilayer perceptron. A toy model in inflation with multiple light fields is investigated numerically as an example of such an application.},

  doi          = {10.1007/jhep12(2017)149},

  journal      = {Journal of High Energy Physics (Online)},

  number       = 12,

  volume       = 2017,

  place        = {United States},

  year         = {Thu Dec 28 00:00:00 EST 2017},

  month        = {Thu Dec 28 00:00:00 EST 2017}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1007/jhep12(2017)149

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 13 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Encyclopædia Inflationaris
journal, December 2014

Martin, Jérôme; Ringeval, Christophe; Vennin, Vincent
Physics of the Dark Universe, Vol. 5-6
DOI: 10.1016/j.dark.2014.01.003

The Cosmological Constant Problem and Inflation in the String Landscape
journal, April 2009

Huang, Qing-Guo; Henry Tye, S. -H.
International Journal of Modern Physics A, Vol. 24, Issue 10
DOI: 10.1142/S0217751X0904316X

A new inflationary universe scenario: A possible solution of the horizon, flatness, homogeneity, isotropy and primordial monopole problems
journal, February 1982

Linde, A. D.
Physics Letters B, Vol. 108, Issue 6
DOI: 10.1016/0370-2693(82)91219-9

On Gaussian random supergravity
journal, April 2014

Bachlechner, Thomas C.
Journal of High Energy Physics, Vol. 2014, Issue 4
DOI: 10.1007/JHEP04(2014)054

Approximation capabilities of multilayer feedforward networks
journal, January 1991

Hornik, Kurt
Neural Networks, Vol. 4, Issue 2
DOI: 10.1016/0893-6080(91)90009-T

Disorder in the early universe
journal, March 2015

Green, Daniel
Journal of Cosmology and Astroparticle Physics, Vol. 2015, Issue 03
DOI: 10.1088/1475-7516/2015/03/020

The statistics of peaks of Gaussian random fields
journal, May 1986

Bardeen, J. M.; Bond, J. R.; Kaiser, N.
The Astrophysical Journal, Vol. 304
DOI: 10.1086/164143

Basic results in vacuum statistics
journal, November 2004

Douglas, Michael R.
Comptes Rendus Physique, Vol. 5, Issue 9-10
DOI: 10.1016/j.crhy.2004.09.008

Quasi-single field inflation and non-Gaussianities
journal, April 2010

Chen, Xingang; Wang, Yi
Journal of Cosmology and Astroparticle Physics, Vol. 2010, Issue 04
DOI: 10.1088/1475-7516/2010/04/027

Inflationary universe: A possible solution to the horizon and flatness problems
journal, January 1981

Guth, Alan H.
Physical Review D, Vol. 23, Issue 2
DOI: 10.1103/PhysRevD.23.347

Computational complexity of the landscape: Part I
journal, May 2007

Denef, Frederik; Douglas, Michael R.
Annals of Physics, Vol. 322, Issue 5
DOI: 10.1016/j.aop.2006.07.013

What Would We Learn by Detecting a Gravitational Wave Signal in the Cosmic Microwave Background Anisotropy?
journal, March 1997

Lyth, David H.
Physical Review Letters, Vol. 78, Issue 10
DOI: 10.1103/PhysRevLett.78.1861

Machine learning in the string landscape
journal, September 2017

Carifio, Jonathan; Halverson, James; Krioukov, Dmitri
Journal of High Energy Physics, Vol. 2017, Issue 9
DOI: 10.1007/JHEP09(2017)157

Beauty is distractive: particle production during multifield inflation
journal, August 2011

Battefeld, Diana; Battefeld, Thorsten; Byrnes, Christian
Journal of Cosmology and Astroparticle Physics, Vol. 2011, Issue 08
DOI: 10.1088/1475-7516/2011/08/025

Stochastic de sitter (inflationary) stage in the early universe
book, January 1988

Starobinsky, A. A.
Field Theory, Quantum Gravity and Strings
DOI: 10.1007/3-540-16452-9_6

Cosmology for Grand Unified Theories with Radiatively Induced Symmetry Breaking
journal, April 1982

Albrecht, Andreas; Steinhardt, Paul J.
Physical Review Letters, Vol. 48, Issue 17
DOI: 10.1103/PhysRevLett.48.1220

Approximation by superpositions of a sigmoidal function
journal, December 1989

Cybenko, G.
Mathematics of Control, Signals, and Systems, Vol. 2, Issue 4
DOI: 10.1007/BF02551274

The string landscape, black holes and gravity as the weakest force
journal, June 2007

Arkani-Hamed, Nima; Motl, Luboš; Nicolis, Alberto
Journal of High Energy Physics, Vol. 2007, Issue 06
DOI: 10.1088/1126-6708/2007/06/060

Energy landscapes for machine learning
journal, January 2017

Ballard, Andrew J.; Das, Ritankar; Martiniani, Stefano
Physical Chemistry Chemical Physics, Vol. 19, Issue 20
DOI: 10.1039/C7CP01108C

Multi-field inflation with random potentials: field dimension, feature scale and non-Gaussianity
journal, February 2012

Frazer, Jonathan; Liddle, Andrew R.
Journal of Cosmology and Astroparticle Physics, Vol. 2012, Issue 02
DOI: 10.1088/1475-7516/2012/02/039

Vacuum configurations for superstrings
journal, January 1985

Candelas, P.; Horowitz, Gary T.; Strominger, Andrew
Nuclear Physics B, Vol. 258
DOI: 10.1016/0550-3213(85)90602-9

A neural-network based estimator to search for primordial non-Gaussianity in Planck CMB maps
journal, September 2015

Novaes, C. P.; Bernui, A.; Ferreira, I. S.
Journal of Cosmology and Astroparticle Physics, Vol. 2015, Issue 09
DOI: 10.1088/1475-7516/2015/09/064

Local random potentials of high differentiability to model the Landscape
journal, March 2015

Battefeld, T.; Modi, C.
Journal of Cosmology and Astroparticle Physics, Vol. 2015, Issue 03
DOI: 10.1088/1475-7516/2015/03/010

Machine learning of Calabi-Yau volumes
journal, September 2017

Krefl, Daniel; Seong, Rak-Kyeong
Physical Review D, Vol. 96, Issue 6
DOI: 10.1103/PhysRevD.96.066014

Cosmology from random multifield potentials
journal, March 2006

Aazami, Amir; Easther, Richard
Journal of Cosmology and Astroparticle Physics, Vol. 2006, Issue 03
DOI: 10.1088/1475-7516/2006/03/013

de Sitter vacua in string theory
journal, August 2003

Kachru, Shamit; Kallosh, Renata; Linde, Andrei
Physical Review D, Vol. 68, Issue 4
DOI: 10.1103/PhysRevD.68.046005

Multi-stream inflation in a landscape
journal, April 2012

Duplessis, Francis; Wang, Yi; Brandenberger, Robert
Journal of Cosmology and Astroparticle Physics, Vol. 2012, Issue 04
DOI: 10.1088/1475-7516/2012/04/012

Charting an Inflationary Landscape with Random Matrix Theory
journal, November 2013

Marsh, M. C. David; McAllister, Liam; Pajer, Enrico
Journal of Cosmology and Astroparticle Physics, Vol. 2013, Issue 11
DOI: 10.1088/1475-7516/2013/11/040

Machine learning phases of matter
journal, February 2017

Carrasquilla, Juan; Melko, Roger G.
Nature Physics, Vol. 13, Issue 5
DOI: 10.1038/nphys4035

Evolving neural networks with genetic algorithms to study the string landscape
journal, August 2017

Ruehle, Fabian
Journal of High Energy Physics, Vol. 2017, Issue 8
DOI: 10.1007/JHEP08(2017)038

The Joys of Haar Measure
book, January 2013

Diestel, Joe; Spalsbury, Angela
DOI: 10.1090/gsm/150

Der Massbegriff in der Theorie der Kontinuierlichen Gruppen
journal, January 1933

Haar, Alfred
The Annals of Mathematics, Vol. 34, Issue 1
DOI: 10.2307/1968346

Multifield consequences for D-brane inflation
journal, June 2012

Dias, Mafalda; Frazer, Jonathan; Liddle, Andrew R.
Journal of Cosmology and Astroparticle Physics, Vol. 2012, Issue 06
DOI: 10.1088/1475-7516/2012/06/020

A neural network clustering algorithm for the ATLAS silicon pixel detector
journal, September 2014

collaboration, The ATLAS
Journal of Instrumentation, Vol. 9, Issue 09
DOI: 10.1088/1748-0221/9/09/P09009

Works referencing / citing this record:

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
journal, September 2019

Fluke, Christopher J.; Jacobs, Colin
WIREs Data Mining and Knowledge Discovery, Vol. 10, Issue 2
DOI: 10.1002/widm.1349

Similar Records in DOE PAGES and OSTI.GOV collections:

Artificial neural network implementation of chemistry with pdf simulation of H{sub 2}/CO{sub 2} flames

Journal Article Christo, F C ; Masri, A R ; Nebot, E M - Combustion and Flame

A novel approach using artificial neural networks for representing chemical reactions is developed and successfully implemented with a modeled velocity-scalar joint pdf transport equation for H{sub 2}CO{sub 2} turbulent jet diffusion flames. The chemical kinetics are represented using a three-step reduced mechanism, and the transport equation is solved by a Monte Carlo method. A detailed analysis of computational performance and a comparison between the neural network approach and other methods used to represent the chemistry, namely the look-up table, or the direct integration procedures, are presented. A multilayer perceptron architecture is chosen for the neural network. The training algorithm ismore »« less
https://doi.org/10.1016/0010-2180(95)00250-2
A mathematical discussion concerning the performance of multilayer perceptron-type artificial neural networks through use of orthogonal bipolar vectors

Journal Article Manzan, José Ricardo Gonçalves, E-mail: josericardo@iftm.edu.br ; Yamanaka, Keiji ; Peretta, Igor Santos, E-mail: iperetta@gmail.com ; ... - Computational and Applied Mathematics

This work proposes the use of orthogonal bipolar vectors (OBV) as targets for multilayer perceptron (MLP) Artificial neural networks pertaining to the pattern recognition field. Implications involving this proposal are supported by a proper mathematical discussion. This study shows that the use of OBV as targets improves the class identification performance of MLP networks for pattern recognition with more than two classes when compared to the widely used conventional target bipolar vector (CBV). In addition to the overall performance improvement, it is possible to obtain high recognition rates with fewer training epochs, while keeping a feasible generalization with other data.more »« less
https://doi.org/10.1007/S40314-016-0377-X
An Artificial Neural Network Model to Predict the Bainite Plate Thickness of Nanostructured Bainitic Steels Using an Efficient Network-Learning Algorithm

Journal Article Shah, Minal ; Das, Suchandan K. - Journal of Materials Engineering and Performance

Nanostructured bainitic steel has an extraordinary ultrahigh strength of about 2.0 GPa along with good toughness of 30 MPa m{sup 1/2}. The finer thickness of plate 20-80 nm is largely responsible for achieving such a large hardness of 690-720 HV. In this work, a multilayer perceptron-based artificial neural network (ANN) model has been developed to predict the thickness of bainite plate pertaining to nanostructured bainitic steels. The inputs of the ANN model are, namely, Gibbs free energy for bainitic transformation, austenite strength, transformation temperature for bainite and carbon concentration in the steel. The model prediction revealed that the bainite plate thickness critically depends on austenite strengthmore »« less
https://doi.org/10.1007/S11665-018-3696-9
Nuclear power plant transient diagnostics using artificial neural networks that allow ``don`t-know`` classifications

Journal Article Bartal, Y ; Lin, J ; Uhrig, R E - Nuclear Technology

A nuclear power plant`s (NPP`s) status is usually monitored by a human operator. Any classifier system used to enhance the operator`s capability to diagnose a safety-critical system like an NPP should classify a novel transient as ``don`t-know`` if it is not contained within its accumulated knowledge base. In particular, the classifier needs some kind of proximity measure between the new data and its training set. Artificial neural networks have been proposed as NPP classifiers, the most popular ones being the multilayered perceptron (MLP) type. However, MLPs do not have a proximity measure, while learning vector quantization, probabilistic neural networks (PNNs),more »« less
Acceleration of the learning of artificial neural networks utilizing a thermodynamic and kinetic model with applications in sensor data processing

Miscellaneous Xu, Xiaoshu

Signal detection and classification are very important in industrial applications, especially in real-time sensor data processing. Traditional techniques cannot process these sensor data very well in industrial applications because of high noise and a large amount of information requiring parallel processing to achieve sufficient throughput. Artificial neural networks are a new technique to solve this problem. However, the commonly used back-propagation neural network typically has a very slow learning rate, and learning instabilities that make the learning unpredictable. The author studied both problems from a mathematical view point as well as a thermodynamic/kinetics view point, and derived a new learningmore »« less

Similar Records

Title: Artificial neural network in cosmic landscape

Abstract

Citation Formats

Encyclopædia Inflationaris journal, December 2014

The Cosmological Constant Problem and Inflation in the String Landscape journal, April 2009

A new inflationary universe scenario: A possible solution of the horizon, flatness, homogeneity, isotropy and primordial monopole problems journal, February 1982

On Gaussian random supergravity journal, April 2014

Approximation capabilities of multilayer feedforward networks journal, January 1991

Disorder in the early universe journal, March 2015

The statistics of peaks of Gaussian random fields journal, May 1986

Basic results in vacuum statistics journal, November 2004

Quasi-single field inflation and non-Gaussianities journal, April 2010

Inflationary universe: A possible solution to the horizon and flatness problems journal, January 1981

Computational complexity of the landscape: Part I journal, May 2007

What Would We Learn by Detecting a Gravitational Wave Signal in the Cosmic Microwave Background Anisotropy? journal, March 1997

Machine learning in the string landscape journal, September 2017

Beauty is distractive: particle production during multifield inflation journal, August 2011

Stochastic de sitter (inflationary) stage in the early universe book, January 1988

Cosmology for Grand Unified Theories with Radiatively Induced Symmetry Breaking journal, April 1982

Approximation by superpositions of a sigmoidal function journal, December 1989

The string landscape, black holes and gravity as the weakest force journal, June 2007

Energy landscapes for machine learning journal, January 2017

Multi-field inflation with random potentials: field dimension, feature scale and non-Gaussianity journal, February 2012

Vacuum configurations for superstrings journal, January 1985

A neural-network based estimator to search for primordial non-Gaussianity in Planck CMB maps journal, September 2015

Local random potentials of high differentiability to model the Landscape journal, March 2015

Machine learning of Calabi-Yau volumes journal, September 2017

Cosmology from random multifield potentials journal, March 2006

de Sitter vacua in string theory journal, August 2003

Multi-stream inflation in a landscape journal, April 2012

Charting an Inflationary Landscape with Random Matrix Theory journal, November 2013

Machine learning phases of matter journal, February 2017

Evolving neural networks with genetic algorithms to study the string landscape journal, August 2017

The Joys of Haar Measure book, January 2013

Der Massbegriff in der Theorie der Kontinuierlichen Gruppen journal, January 1933

Multifield consequences for D-brane inflation journal, June 2012

A neural network clustering algorithm for the ATLAS silicon pixel detector journal, September 2014

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy journal, September 2019

Encyclopædia Inflationaris
journal, December 2014

The Cosmological Constant Problem and Inflation in the String Landscape
journal, April 2009

A new inflationary universe scenario: A possible solution of the horizon, flatness, homogeneity, isotropy and primordial monopole problems
journal, February 1982

On Gaussian random supergravity
journal, April 2014

Approximation capabilities of multilayer feedforward networks
journal, January 1991

Disorder in the early universe
journal, March 2015

The statistics of peaks of Gaussian random fields
journal, May 1986

Basic results in vacuum statistics
journal, November 2004

Quasi-single field inflation and non-Gaussianities
journal, April 2010

Inflationary universe: A possible solution to the horizon and flatness problems
journal, January 1981

Computational complexity of the landscape: Part I
journal, May 2007

What Would We Learn by Detecting a Gravitational Wave Signal in the Cosmic Microwave Background Anisotropy?
journal, March 1997

Machine learning in the string landscape
journal, September 2017

Beauty is distractive: particle production during multifield inflation
journal, August 2011

Stochastic de sitter (inflationary) stage in the early universe
book, January 1988

Cosmology for Grand Unified Theories with Radiatively Induced Symmetry Breaking
journal, April 1982

Approximation by superpositions of a sigmoidal function
journal, December 1989

The string landscape, black holes and gravity as the weakest force
journal, June 2007

Energy landscapes for machine learning
journal, January 2017

Multi-field inflation with random potentials: field dimension, feature scale and non-Gaussianity
journal, February 2012

Vacuum configurations for superstrings
journal, January 1985

A neural-network based estimator to search for primordial non-Gaussianity in Planck CMB maps
journal, September 2015

Local random potentials of high differentiability to model the Landscape
journal, March 2015

Machine learning of Calabi-Yau volumes
journal, September 2017

Cosmology from random multifield potentials
journal, March 2006

de Sitter vacua in string theory
journal, August 2003

Multi-stream inflation in a landscape
journal, April 2012

Charting an Inflationary Landscape with Random Matrix Theory
journal, November 2013

Machine learning phases of matter
journal, February 2017

Evolving neural networks with genetic algorithms to study the string landscape
journal, August 2017

The Joys of Haar Measure
book, January 2013

Der Massbegriff in der Theorie der Kontinuierlichen Gruppen
journal, January 1933

Multifield consequences for D-brane inflation
journal, June 2012

A neural network clustering algorithm for the ATLAS silicon pixel detector
journal, September 2014

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
journal, September 2019