Neural network reconstruction of scalar-tensor cosmology

2023/05/24 by Konstantinos F. Dialektopoulos, Dialektopoulos, Konstantinos F., Purba Mukherjee +5 · 1 citation
Computer Science · Physics and Astronomy · #Computational Physics and Python Applications #Cosmology and Gravitation Theories #FOS: Physical sciences #General Relativity and Quantum Cosmology (gr-qc) #Particle physics theoretical and experimental studies

paper · pdf · doi:10.48550/arxiv.2305.15500

openalex publication_date 2023/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Neural networks have shown great promise in providing a data-first approach to exploring new physics. In this work, we use the full implementation of late time cosmological data to reconstruct a number of scalar-tensor cosmological models within the context of neural network systems. In this pipeline, we incorporate covariances in the data in the neural network training algorithm, rather than a likelihood which is the approach taken in Markov chain Monte Carlo analyses. For general subclasses of classic scalar-tensor models, we find stricter bounds on functional models which may help in the understanding of which models are observationally viable.

Cited by

• Cosmo-Learn: code for learning cosmology using different methods and mock data

Related

• A duality connecting neural network and cosmological dynamics
• How many simulations do we need for simulation-based inference in cosmology?
• Cosmo-PINN: A Physics-Informed Neural Network for Cosmological Reconstruction
• Neural networks as optimal estimators to marginalize over baryonic effects
• Neural networks as a tool for parameter estimation in astrophysical data