{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:14:46Z","timestamp":1776680086497,"version":"3.51.2"},"reference-count":44,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T00:00:00Z","timestamp":1661817600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T00:00:00Z","timestamp":1661817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We demonstrate that the dynamics of neural networks (NNs) trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly related. This duality provides the framework for synergies between these systems, to understand and explain NN dynamics and new ways of simulating and describing early Universe models. Working in the continuous-time limit of NNs, we analytically match the dynamics of the mean background and the dynamics of small perturbations around the mean field, highlighting potential differences in separate limits. We perform empirical tests of this analytic description and quantitatively show the dependence of the effective field theory parameters on hyperparameters of the NN. As a result of this duality, the cosmological constant is matched inversely to the learning rate in the gradient descent update.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac87e9","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T22:25:48Z","timestamp":1659997548000},"page":"035011","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["A duality connecting neural network and cosmological dynamics"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6374-6828","authenticated-orcid":true,"given":"Sven","family":"Krippendorf","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8362-0576","authenticated-orcid":true,"given":"Michael","family":"Spannowsky","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,8,30]]},"reference":[{"key":"mlstac87e9bib1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","article-title":"Some methods of speeding up the convergence of iteration methods","volume":"4","author":"Polyak","year":"1964","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"mlstac87e9bib2","author":"Mukhanov","year":"2005"},{"key":"mlstac87e9bib3","author":"Weinberg","year":"2008"},{"key":"mlstac87e9bib4","author":"Baumann","year":"2009"},{"key":"mlstac87e9bib5","doi-asserted-by":"publisher","first-page":"083C01","DOI":"10.1093\/ptep\/ptaa104","article-title":"Review of particle physics","volume":"2020","author":"Zyla","year":"2020","journal-title":"Prog. Theor. Exp. Phys."},{"key":"mlstac87e9bib6","article-title":"Neural tangent kernel: convergence and generalization in neural networks","author":"Jacot","year":"2018"},{"key":"mlstac87e9bib7","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/abc62b","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume":"2020","author":"Lee","year":"2020","journal-title":"J. Stat. Mech.: Theory Exp."},{"key":"mlstac87e9bib8","article-title":"Neural tangents: fast and easy infinite neural networks in Python","author":"Novak","year":"2019"},{"key":"mlstac87e9bib9","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/0370-2693(83)90837-7","article-title":"Chaotic inflation","volume":"129","author":"Linde","year":"1983","journal-title":"Phys. Lett. B"},{"key":"mlstac87e9bib10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","article-title":"On the momentum term in gradient descent learning algorithms","volume":"12","author":"Qian","year":"1999","journal-title":"Neural Netw."},{"key":"mlstac87e9bib11","first-page":"5312","article-title":"A differential equation for modeling nesterov\u2019s accelerated gradient method: theory and insights","volume":"17","author":"Su","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac87e9bib12","article-title":"The principles of deep learning theory","author":"Roberts","year":"2021"},{"key":"mlstac87e9bib13","volume":"vol 118","author":"Neal","year":"2012"},{"key":"mlstac87e9bib14","article-title":"Deep neural networks as Gaussian processes","author":"Lee","year":"2017"},{"key":"mlstac87e9bib15","article-title":"Gaussian process behaviour in wide deep neural networks","author":"Matthews","year":"2018"},{"key":"mlstac87e9bib16","article-title":"Bayesian deep convolutional networks with many channels are Gaussian processes","author":"Novak","year":"2018"},{"key":"mlstac87e9bib17","article-title":"Deep convolutional networks as shallow Gaussian processes","author":"Garriga-Alonso","year":"2018"},{"key":"mlstac87e9bib18","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abeca3","article-title":"Neural networks and quantum field theory","volume":"2","author":"Halverson","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstac87e9bib19","article-title":"Symmetry-via-duality: invariant neural network densities from parameter-space correlators","author":"Maiti","year":"2021"},{"key":"mlstac87e9bib20","article-title":"Nonperturbative renormalization for the neural network-QFT correspondence","author":"Erbin","year":"2021"},{"key":"mlstac87e9bib21","article-title":"Building quantum field theories out of neurons","author":"Halverson","year":"2021"},{"key":"mlstac87e9bib22","doi-asserted-by":"publisher","first-page":"081","DOI":"10.21468\/SciPostPhys.12.3.081","article-title":"The edge of chaos: quantum field theory and deep neural networks","volume":"12","author":"Grosvenor","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstac87e9bib23","article-title":"Representation learning via quantum neural tangent kernels","author":"Liu","year":"2021"},{"key":"mlstac87e9bib24","article-title":"Infinite neural network quantum states","author":"Luo","year":"2021"},{"key":"mlstac87e9bib25","article-title":"Asymptotics of wide networks from Feynman diagrams","author":"Dyer","year":"2019"},{"key":"mlstac87e9bib26","article-title":"Feature learning in infinite-width neural networks","author":"Yang","year":"2021"},{"key":"mlstac87e9bib27","article-title":"Tensor programs I: wide feedforward or recurrent neural networks of any architecture are Gaussian processes","author":"Yang","year":"2021"},{"key":"mlstac87e9bib28","article-title":"Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation","author":"Yang","year":"2020"},{"key":"mlstac87e9bib29","article-title":"Tensor programs II: neural tangent kernel for any architecture","author":"Yang","year":"2020"},{"key":"mlstac87e9bib30","article-title":"Tensor programs III: neural matrix laws","author":"Yang","year":"2020"},{"key":"mlstac87e9bib31","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/0370-1573(92)90044-Z","article-title":"Theory of cosmological perturbations. Part 1. Classical perturbations. Part 2. Quantum theory of perturbations. Part 3. Extensions","volume":"215","author":"Mukhanov","year":"1992","journal-title":"Phys. Rep."},{"key":"mlstac87e9bib32","article-title":"Born-Infeld (BI) for AI: energy-conserving descent (ECD) for optimization","author":"De Luca","year":"2022"},{"key":"mlstac87e9bib33","doi-asserted-by":"publisher","first-page":"12","DOI":"10.12942\/lrr-2005-12","article-title":"Analogue gravity","volume":"8","author":"Barcelo","year":"2005","journal-title":"Living Rev. Relativ."},{"key":"mlstac87e9bib34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.111.031301","article-title":"Cosmology from group field theory formalism for quantum gravity","volume":"111","author":"Gielen","year":"2013","journal-title":"Phys. Rev. Lett."},{"key":"mlstac87e9bib35","doi-asserted-by":"publisher","first-page":"231","DOI":"10.4310\/ATMP.1998.v2.n2.a1","article-title":"The large N limit of superconformal field theories and supergravity","volume":"2","author":"Maldacena","year":"1998","journal-title":"Adv. Theor. Math. Phys."},{"key":"mlstac87e9bib36","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/JHEP04(2011)029","article-title":"On the origin of gravity and the laws of newton","volume":"2011","author":"Verlinde","year":"2011","journal-title":"J. High Energy Phys."},{"key":"mlstac87e9bib37","first-page":"pp 149","article-title":"The cosmological constant problem: why it\u2019s hard to get dark energy from micro-physics","author":"Burgess","year":"2015"},{"key":"mlstac87e9bib38","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.aop.2019.04.011","article-title":"Variable polytropic gas cosmology","volume":"407","author":"Salti","year":"2019","journal-title":"Ann. Phys., NY"},{"key":"mlstac87e9bib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.dark.2019.100369","article-title":"Machine learning algorithm in a caloric view point of cosmology","volume":"26","author":"Kangal","year":"2019","journal-title":"Phys. Dark Universe"},{"key":"mlstac87e9bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2020.107809","article-title":"Deep learning approach to Hubble parameter","volume":"261","author":"Tilaver","year":"2021","journal-title":"Comput. Phys. Commun."},{"key":"mlstac87e9bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2021.100504","article-title":"Evolution of CMB temperature in a Chaplygin gas model from deep learning perspective","volume":"37","author":"Salti","year":"2021","journal-title":"Astron. Comput."},{"key":"mlstac87e9bib42","doi-asserted-by":"publisher","DOI":"10.1016\/j.aop.2022.168799","article-title":"Deep learning of CMB radiation temperature","volume":"439","author":"Salti","year":"2022","journal-title":"Ann. Phys., NY"},{"key":"mlstac87e9bib43","doi-asserted-by":"crossref","article-title":"GADGET: a code for collisionless and gasdynamical cosmological simulations","author":"Springel","DOI":"10.1016\/S1384-1076(01)00042-2"},{"key":"mlstac87e9bib44","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1016\/j.cpc.2008.02.009","article-title":"LATTICEEASY: a program for lattice simulations of scalar fields in an expanding universe","volume":"178","author":"Felder","year":"2008","journal-title":"Comput. Phys. Commun."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T13:48:05Z","timestamp":1661867285000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac87e9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,30]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,8,30]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac87e9","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,30]]},"assertion":[{"value":"A duality connecting neural network and cosmological dynamics","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-05-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-08-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-08-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}