Related papers: Evaluating Physically Motivated Loss Functions for…
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low…
The need to analyze the available large synoptic multi-band surveys drives the development of new data-analysis methods. Photometric redshift estimation is one field of application where such new methods improved the results, substantially.…
We review the use of photometric redshifts in the particular context of Gravitational Telescopes. We discuss on the possible application of such a technique to the study of both the faint population of distant sources and the properties of…
This article deals with the realisation of constraints in underdamped Langevin dynamics via soft-constrained dynamics. Specifically, we study systems with a large (or small) parameter that controls the constraint mechanisms, e.g. the…
We present a supervised neural network approach to the determination of photometric redshifts. The method was tuned to match the characteristics of the Sloan Digital Sky Survey and it exploits the spectroscopic redshifts provided by this…
We investigate the cosmological dependence and the constraining power of large-scale galaxy correlations, including all redshift-distortions, wide-angle, lensing and gravitational potential effects on linear scales. We analyze the…
A goal of forthcoming imaging surveys is to use weak gravitational lensing shear measurements to constrain dark energy. We quantify the importance of uncalibrated photometric redshift outliers to the dark energy goals of forthcoming imaging…
We use the cosmic shear data from the Canada-France-Hawaii Telescope Lensing Survey to place constraints on $f(R)$ and {\it Generalized Dilaton} models of modified gravity. This is highly complimentary to other probes since the constraints…
In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate…
Obtaining accurate photometric redshift estimations is an important aspect of cosmology, remaining a prerequisite of many analyses. In creating novel methods to produce redshift estimations, there has been a shift towards using machine…
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…
We calculate photometric redshifts from the Sloan Digital Sky Survey Data Release 2 Galaxy Sample using artificial neural networks (ANNs). Different input patterns based on various parameters (e.g. magnitude, color index, flux information)…
Over the next decade, improvements in cosmological parameter constraints will be driven by surveys of large-scale structure. Its inherent non-linearity suggests that significant information will be embedded in higher correlations beyond the…
Many real life optimization problems contain both hard and soft constraints, as well as qualitative conditional preferences. However, there is no single formalism to specify all three kinds of information. We therefore propose a framework,…
Based on the Sloan Digital Sky Survey Data Release 5 Galaxy Sample, we explore photometric morphology classification and redshift estimation of galaxies using photometric data and known spectroscopic redshifts. An unsupervised method,…
The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations…
Recent studies have shown that regularization techniques using soft labels, e.g., label smoothing, Mixup, and CutMix, not only enhance image classification accuracy but also mitigate miscalibration due to overconfident predictions, and…
Future large scale structure surveys will provide increasingly tight constraints on our cosmological model. These surveys will report results on the distance scale and growth rate of perturbations through measurements of Baryon Acoustic…
Cosmological weak lensing gives rise to correlations in the ellipticities of faint galaxies. This cosmic shear signal depends upon the matter power spectrum, thus providing a means to constrain cosmological parameters. It has recently been…
A new approach to estimating photometric redshifts - using Artificial Neural Networks (ANNs) - is investigated. Unlike the standard template-fitting photometric redshift technique, a large spectroscopically-identified training set is…