A deep learning approach to cosmological dark energy models

Abstract

We propose a novel deep learning tool in order to study the evolution of dark energy models. The aim is to combine two architectures: the Recurrent Neural Networks (RNN) and the Bayesian Neural Networks (BNN), we named this full network as RNN+BNN. The first one is capable of learning complex sequential information to classify objects like supernovae and use the light-curves directly to learn information from the sequence of observations. Since RNN is not capable to calculate the uncertainties, BNN emerges as a solution for problems in deep learning like, for example, the overfitting. For the trainings we use measurements of the distance modulus $\mu (z)$, such as those provided by Pantheon Supernovae Type Ia. In view of our results, the reported approach turns out to be a first promising step on how we can train a new neural network that can compute their own confidence regions for specific cosmological data. It is worth stressing that the new technique allows to reduce the computational load of expensive codes for dark energy models and probe the necessity of modified dark energy models at large redshifts for a supernovae trained sampler.

arXiv comment22 pages, 8 figures. Version accepted for publication in JCAP

References in corpus (44)

• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• The Cosmological Constant and Dark Energy
• An overview of gradient descent optimization algorithms
• The Complete Light-curve Sample of Spectroscopically Confirmed Type Ia Supernovae from Pan-STARRS1 and Cosmological Constraints from The Combined Pantheon Sample
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Accelerating Universes with Scaling Dark Matter
• A Dynamical Solution to the Problem of a Small Cosmological Constant and Late-time Cosmic Acceleration
• Curvature Quintessence
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Beyond $\Lambda$CDM: Problems, solutions, and the road ahead
• Dynamical dark energy in light of the latest observations
• Probing the dark energy: methods and strategies
• How many cosmological parameters?
• Reconstruction of dark energy and expansion dynamics using Gaussian processes
• Extended Gravity Cosmography
• Applications of Bayesian model selection to cosmological parameters
• The Dynamics of Quintessence, The Quintessence of Dynamics
• The Three-Point Correlation Function in Cosmology
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Figure of Merit for Dark Energy Constraints from Current Observational Data
• Comparison of non-linear activation functions for deep neural networks on MNIST classification task
• Deep Recurrent Neural Networks for Supernovae Classification
• Reinforcement Learning Neural Turing Machines - Revised
• Present and future evidence for evolving dark energy
• The WiggleZ Dark Energy Survey: constraining galaxy bias and cosmic growth with 3-point correlation functions
• Reconstruction of the Dark Energy equation of state
• SN and BAO constraints on (new) polynomial dark energy parametrizations: current results and forecasts
• Unveiling cosmography from the dark energy equation of state
• Modified gravity for surveys
• Observational Constraints on Modified Chaplygin Gas from Cosmic Growth
• Nonparametric reconstruction of the cosmic expansion with local regression smoothing and simulation extrapolation
• The Role of Machine Learning in the Next Decade of Cosmology
• Accelerated Bayesian inference using deep learning
• Status on bidimensional dark energy parameterizations using SNe Ia JLA and BAO datasets
• Cosmological model discrimination with Deep Learning
• CosmoFlow: Using Deep Learning to Learn the Universe at Scale
• Supernova Photometric Classification Challenge
• Note on the equation of state of geometric dark-energy in f(R) gravity
• Tension between SN and BAO: current status and future forecasts
• $f(R)$ gravity modifications: from the action to the data
• Improved Photometric Classification of Supernovae using Deep Learning
• Model-independent constraints on dark energy and modified gravity with the SKA
• Constraints to dark energy using PADE parameterisations

Cited by in corpus (57)

• Teleparallel Gravity: From Theory to Cosmology
• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• High-redshift cosmography: auxiliary variables versus Padé polynomials
• Barrow holographic dark energy with Hubble horizon as IR cutoff
• What can Machine Learning tell us about the background expansion of the Universe?
• An analysis of the $H_0$ tension problem in a universe with a viscous dark fluid
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Convolutional Neural Networks for Direct Detection of Dark Matter
• Neural network reconstructions for the Hubble parameter, growth rate and distance modulus
• Cosmographic view on the $H_0$ and ${\sigma }_8$ tensions
• Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
• Observational cosmology with Artificial Neural Networks
• Neural Network Reconstruction of $H^{\prime }(z)$ and its application in Teleparallel Gravity
• Recovering the CMB Signal with Machine Learning
• Generalized interacting Barrow Holographic Dark Energy: cosmological predictions and thermodynamic considerations
• Model-independent test for the cosmic distance duality relation with Pantheon and eBOSS DR16 quasar sample
• Model-independently calibrating the luminosity correlations of gamma-ray bursts using deep learning
• Neural networks and standard cosmography with newly calibrated high redshift GRB observations
• Likelihood-free Inference with Mixture Density Network
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• LSST Cadence Strategy Evaluations for AGN Time-series Data in Wide-Fast-Deep Field
• Cosmology-informed neural networks to solve the background dynamics of the Universe
• Using Machine Learning to disentangle LHC signatures of Dark Matter candidates
• Inverse Cosmography: testing the effectiveness of cosmographic polynomials using machine learning
• Cosmic Growth in $f(T)$ Teleparallel Gravity
• LeMoN: Lens Modelling with Neural networks -- I. Automated modelling of strong gravitational lenses with Bayesian Neural Networks
• Cosmological constraints of Palatini $f(\mathcal{R})$ gravity
• Deep learning method in testing the cosmic distance duality relation
• Exploring bulk viscous unified scenarios with Gravitational Waves Standard Sirens
• Minimal model dependent constraints on cosmological nuisance parameters and cosmic curvature from combinations of cosmological data
• A possible late-time transition of $M_B$ inferred via neural networks
• Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory
• Discriminating among cosmological models by data-driven methods
• Reconstructing the Hubble diagram of gamma-ray bursts using deep learning
• Detection of Dipole Modulation in CMB Temperature Anisotropy Maps from WMAP and Planck using Artificial Intelligence
• Constraining Coupling Constants' Variation with Supernovae, Quasars, and GRBs
• An approach to cold dark matter deviation and the $H_0$ tension problem by using machine learning
• Observational constraints on complex quintessence with attractive self-interaction
• Estimation of Full Sky Power Spectrum between Intermediate to Large Angular Scales from Partial Sky CMB Anisotropies using Artificial Neural Network
• Faster Bayesian inference with neural network bundles and new results for $f(R)$ models
• A machine learning-based methodology for pulse classification in dual-phase xenon time projection chambers
• Bayesian deep learning for dark energy
• Studying Lagrangian theories with machine learning: a toy model
• Clusternets: A deep learning approach to probe clustering dark energy
• Linear perturbations spectra for dynamical dark energy inspired by modified gravity
• ParamANN: A Neural Network to Estimate Cosmological Parameters for $\Lambda$CDM Universe Using Hubble Measurements
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• Reconstruction of full sky CMB $\mathbf{E}$ and $\mathbf{B}$ modes spectra removing $\mathbf{E}$-to-$\mathbf{B}$ leakage from partial sky using deep learning
• Phantom scalar field cosmologies constrained by early cosmic measurements
• Gamma-Ray Bursts Calibrated by Using Artificial Neural Networks from the Pantheon+ Sample
• Strengthening interacting agegraphic dark energy DGP constraints with local measurements and multimessenger forecastings
• SageNet: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation
• Inferring the spin distribution of binary black holes using deep learning
• Evolution of linear matter perturbations with error-bounded bundle physics-informed neural networks
• Impact of conversion-driven processes on singlet-doublet Majorana dark matter relic
• Machine Learning for Nanohertz Gravitational Wave Detection and Parameter Estimation with Pulsar Timing Array
• Assessing Galaxy Rotation Kinematics: Insights from Convolutional Neural Networks on Velocity Variations