Related papers: Deconfusing intensity maps with neural networks

Line intensity mapping (LIM) is a technique for producing 3D maps of the Universe by scanning the sky with a spectrometer sensitive to a range of wavelengths corresponding to the redshifted spectral lines of atoms or molecules, such as…

Modern cosmological surveys probe the Universe deep into the nonlinear regime, where massive neutrinos suppress cosmic structure. Traditional cosmological analyses, which use the 2-point correlation function to extract information, are no…

Recent studies have shown convolutional neural networks (CNNs) can be trained to perform modal decomposition using intensity images of optical fields. A fundamental limitation of these techniques is that the modal phases can not be uniquely…

We present a code to generate mock observations of 21 cm intensity mapping experiments. The emphasis of the code is on reducing the computational cost of running a full-blown simulation, trading computational time for accuracy. The code can…

Machine learning has the potential to improve the reconstruction of the dark matter profile of galaxies with respect to traditional methods, like rotation curves. We demonstrate on the simulation suite Illustris-TNG that a steerable…

In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks in a situation where the blur kernels are partially constrained. We focus on blurred images from a…

Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue,…

Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment. A heterogeneous set of sensors is used to perform this task robustly. Among them, radar sensors are indispensable because of their…

Recently, convolutional neural networks (CNNs) have been widely used in image denoising. Existing methods benefited from residual learning and achieved high performance. Much research has been paid attention to optimizing the network…

Convolutional neural networks (CNNs) have achieved superior accuracy in many visual related tasks. However, the inference process through intermediate layers is opaque, making it difficult to interpret such networks or develop trust in…

The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to…

Intensity mapping has attracted significant interest as an approach to measure the properties of the interstellar medium in typical galaxies at high redshift. Intensity mapping measures the statistics of surface brightness as a function of…

Convolutional Neural Networks (CNNs) have demonstrated potential for the real-time analysis of data from gravitational-wave detector networks for the specific case of signals from coalescing compact-object binaries such as black-hole…

Line intensity mapping (LIM) is a promising tool to efficiently probe the three-dimensional large-scale structure by mapping the aggregate emission of a spectral line from all sources that trace the matter density field. Spectral lines from…

Weak Lensing (WL) surveys are reaching unprecedented depths, enabling the investigation of very small angular scales. At these scales, nonlinear gravitational effects lead to higher-order correlations making the matter distribution highly…

In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most…

The high accuracy of detector simulation is crucial for modern particle physics experiments. However, this accuracy comes with a high computational cost, which will be exacerbated by the large datasets and complex detector upgrades…

Line Intensity Mapping (LIM) offers a novel avenue to observe and characterize our universe. LIM data of CO spectral lines are becoming available, such as those obtained by the CO Mapping Array Project (COMAP). COMAP data can be used to…

Following the first two annual intensity mapping workshops at Stanford in March 2016 and Johns Hopkins in June 2017, we report on the recent advances in theory, instrumentation and observation that were presented in these meetings and some…

We present an innovative approach to constraining the non-cold dark matter model using a convolutional neural network (CNN). We perform a suite of hydrodynamic simulations with varying dark matter particle masses and generate mock 21cm…