Inferring Cosmic String Tension through the Neural Network Prediction of String Locations in CMB Maps

TL;DR

This paper enhances neural network techniques to more accurately infer cosmic string tension from CMB maps, improving posterior calculations and utilizing residual networks for better predictions.

Contribution

It introduces an improved neural network architecture and a refined method for calculating the posterior distribution of cosmic string tension from CMB data.

Findings

Enhanced neural network with residual architecture improves string location predictions.

More accurate posterior distribution of cosmic string tension Gμ is obtained.

Quantitative improvements demonstrated on simulated CMB maps.

Abstract

In previous work, we constructed a convolutional neural network used to estimate the location of cosmic strings in simulated cosmic microwave background temperature anisotropy maps. We derived a connection between the estimates of cosmic string locations by this neural network and the posterior probability distribution of the cosmic string tension $G\mu$. Here, we significantly improve the calculation of the posterior distribution of the string tension $G\mu$. We also improve our previous plain convolutional neural network by using residual networks. We apply our new neural network and posterior calculation method to maps from the same simulation used in our previous work and quantify the improvement.