Neural Networks Optimized by Genetic Algorithms in Cosmology
arXiv:2209.02685 · doi:10.1103/PhysRevD.107.043509
Abstract
The applications of artificial neural networks in the cosmological field have shone successfully during the past decade, this is due to their great ability of modeling large amounts of datasets and complex nonlinear functions. However, in some cases, their use still remains controversial because their ease of producing inaccurate results when the hyperparameters are not carefully selected. In this paper, to find the optimal combination of hyperparameters to artificial neural networks, we propose to take advantage of the genetic algorithms. As a proof of the concept, we analyze three different cosmological cases to test the performance of the architectures achieved with the genetic algorithms and compare them with the standard process, consisting of a grid with all possible configurations. First, we carry out a model-independent reconstruction of the distance modulus using a type Ia supernovae compilation. Second, the neural networks learn to infer the equation of state for the quintessence model, and finally with the data from a combined redshift catalog the neural networks predict the photometric redshift given six photometric bands (urgizy). We found that the genetic algorithms improve considerably the generation of the neural network architectures, which can ensure more confidence in their physical results because of the better performance in the metrics with respect to the grid method.
arXiv comment15 pages, 4 figures; matches the version published in Physical Review D
References in corpus (32)
- Improved cosmological constraints from a joint analysis of the SDSS-II and SNLS supernova samples
- ParamILS: An Automatic Algorithm Configuration Framework
- Cosmological implications of baryon acoustic oscillation (BAO) measurements
- Reconstructing Dark Energy
- Subaru Prime Focus Camera -- Suprime-Cam --
- 3D-HST: A wide-field grism spectroscopic survey with the Hubble Space Telescope
- The DEEP3 Galaxy Redshift Survey: The Impact of Environment on the Size Evolution of Massive Early-type Galaxies at Intermediate Redshift
- SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
- COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
- DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
- Evolving neural networks with genetic algorithms to study the String Landscape
- Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
- A new perspective on Dark Energy modeling via Genetic Algorithms
- Reconstruction of the Dark Energy equation of state
- Searching the Landscape of Flux Vacua with Genetic Algorithms
- Neural Network Reconstruction of Late-Time Cosmology and Null Tests
- Testing the Mutual Consistency of the Pantheon and SDSS/eBOSS BAO Data Sets with Gaussian Processes
- Fitness Probability Distribution of Bit-Flip Mutation
- Reconstruction of the Dark Energy equation of state from latest data: the impact of theoretical priors
- Constraining the dark energy equation of state using Bayes theorem and the Kullback-Leibler divergence
- Nonparametric reconstruction of the cosmic expansion with local regression smoothing and simulation extrapolation
- Revisiting a non-parametric reconstruction of the deceleration parameter from combined background and the growth rate data
- BAMBI: blind accelerated multimodal Bayesian inference
- Machine Learning meets the redshift evolution of the CMB Temperature
- Observational cosmology with Artificial Neural Networks
- Defying the laws of Gravity I: model-independent reconstruction of the Universe expansion from growth data
- Bayesian model selection on Scalar -Field Dark Energy
- Non-parametric reconstruction of dark energy and cosmic expansion from the Pantheon compilation of type Ia supernovae
- Neural networks and standard cosmography with newly calibrated high redshift GRB observations
- Deep ugrizY Imaging and DEEP2/3 Spectroscopy: A Photometric Redshift Testbed for LSST and Public Release of Data from the DEEP3 Galaxy Redshift Survey
- Reconstruction of late-time cosmology using Principal Component Analysis
- Testing the CDM paradigm with growth rate data and machine learning
Cited by in corpus (17)
- The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
- Model-independent cosmological inference post DESI DR1 BAO measurements
- CDM Tensions: Localising Missing Physics through Consistency Checks
- Cosmological parameter estimation with Genetic Algorithms
- LADDER: Revisiting the Cosmic Distance Ladder with Deep Learning Approaches and Exploring its Applications
- Non-parametric reconstruction of cosmological observables using Gaussian Processes Regression
- Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory
- Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up
- Analysis of Dark Matter Halo Structure Formation in -body Simulations with Machine Learning
- What can we learn about Reionization astrophysical parameters using Gaussian Process Regression?
- Estimating Cosmological Parameters and Reconstructing Hubble Constant with Artificial Neural Networks: A Test with covariance matrix and mock H(z)
- Data-driven modeling of rotation curves with artificial neural networks
- A Quantum Genetic Algorithm with application to Cosmological Parameters Estimation
- Nature-inspired optimization, the Philippine Eagle, and cosmological parameter estimation
- Genetic algorithm demystified for cosmological parameter estimation
- Variational autoencoder for generating realistic -body simulations for dark matter halos
- Neural network ensemble for computing cross sections for rotational transitions in HO + HO collisions