Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit

TL;DR: The ability to better recover detailed features from low-signal-to-noise and low angular resolution imaging data significantly increases the ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope and the Hubble and James Webb space telescopes.

Abstract: Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging data by the Shannon-Nyquist sampling theorem. Here we train a generative adversarial network (GAN) on a sample of $4,550$ images of nearby galaxies at $0.01

TL;DR: A comprehensive overview and analysis of the most recent research in machine learning principles, algorithms, descriptors, and databases in materials science, and proposes solutions and future research paths for various challenges in computational materials science.

Abstract: One of the most exciting tools that have entered the material science toolbox in recent years is machine learning. This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research. At present, we are witnessing an explosion of works that develop and apply machine learning to solid-state systems. We provide a comprehensive overview and analysis of the most recent research in this topic. As a starting point, we introduce machine learning principles, algorithms, descriptors, and databases in materials science. We continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal structure. Then we discuss research in numerous quantitative structure–property relationships and various approaches for the replacement of first-principle methods by machine learning. We review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of applications. Two major questions are always the interpretability of and the physical understanding gained from machine learning models. We consider therefore the different facets of interpretability and their importance in materials science. Finally, we propose solutions and future research paths for various challenges in computational materials science.

TL;DR: Recent experimental work in convolutional neural networks to solve inverse problems in imaging, with a focus on the critical design decisions is reviewed, including sparsity-based techniques such as compressed sensing.

Abstract: In this article, we review recent uses of convolutional neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, superresolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions.

TL;DR: In this paper, the authors review the recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging, including denoising, deconvolution, super-resolution, and medical image reconstruction.

Abstract: In this survey paper, we review recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, super-resolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions: Where does the training data come from? What is the architecture of the CNN? and How is the learning problem formulated and solved? We also bring together a few key theoretical papers that offer perspective on why CNNs are appropriate for inverse problems and point to some next steps in the field.

TL;DR: CaloGAN, a new fast simulation technique based on generative adversarial networks (GANs) is introduced, which is applied to the modeling of electromagnetic showers in a longitudinally segmented calorimeter and achieves speedup factors comparable to or better than existing full simulation techniques.

Abstract: The precise modeling of subatomic particle interactions and propagation through matter is paramount for the advancement of nuclear and particle physics searches and precision measurements. The most computationally expensive step in the simulation pipeline of a typical experiment at the Large Hadron Collider (LHC) is the detailed modeling of the full complexity of physics processes that govern the motion and evolution of particle showers inside calorimeters. We introduce CaloGAN, a new fast simulation technique based on generative adversarial networks (GANs). We apply these neural networks to the modeling of electromagnetic showers in a longitudinally segmented calorimeter and achieve speedup factors comparable to or better than existing full simulation techniques on CPU ($100\ifmmode\times\else\texttimes\fi{}--1000\ifmmode\times\else\texttimes\fi{}$) and even faster on GPU (up to $\ensuremath{\sim}{10}^{5}\ifmmode\times\else\texttimes\fi{}$). There are still challenges for achieving precision across the entire phase space, but our solution can reproduce a variety of geometric shower shape properties of photons, positrons, and charged pions. This represents a significant stepping stone toward a full neural network-based detector simulation that could save significant computing time and enable many analyses now and in the future.

TL;DR: A deep neural network-based generative model is introduced to enable high-fidelity, fast, electromagnetic calorimeter simulation and opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond.

Abstract: Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theoretical modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using existing algorithms and computing resources. The modeling of detectors and the precise description of particle cascades as they interact with the material in the calorimeter are the most computationally demanding steps in the simulation pipeline. We therefore introduce a deep neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation. There are still challenges for achieving precision across the entire phase space, but our current solution can reproduce a variety of particle shower properties while achieving speedup factors of up to 100 000×. This opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond.

TL;DR: An iterative method of restoring degraded images was developed by treating images, point spread functions, and degraded images as probability-frequency functions and by applying Bayes’s theorem.

Abstract: An iterative method of restoring degraded images was developed by treating images, point spread functions, and degraded images as probability-frequency functions and by applying Bayes’s theorem. The method functions effectively in the presence of noise and is adaptable to computer operation.

TL;DR: In this article, a deep convolutional generative adversarial network (GAN) is used to generate plausible images of birds and flowers from detailed text descriptions, translating visual concepts from characters to pixels.

Abstract: Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text and image modeling, translating visual concepts from characters to pixels. We demonstrate the capability of our model to generate plausible images of birds and flowers from detailed text descriptions.

TL;DR: A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels.

Abstract: Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text and image model- ing, translating visual concepts from characters to pixels. We demonstrate the capability of our model to generate plausible images of birds and flowers from detailed text descriptions.

TL;DR: Euclid as mentioned in this paper is a space-based survey mission from the European Space Agency designed to understand the origin of the universe's accelerating expansion, using cosmological probes to investigate the nature of dark energy, dark matter and gravity by tracking their observational signatures.

Abstract: Euclid is a space-based survey mission from the European Space Agency designed to understand the origin of the Universe's accelerating expansion. It will use cosmological probes to investigate the nature of dark energy, dark matter and gravity by tracking their observational signatures on the geometry of the universe and on the cosmic history of structure formation. The mission is optimised for two independent primary cosmological probes: Weak gravitational Lensing (WL) and Baryonic Acoustic Oscillations (BAO). The Euclid payload consists of a 1.2 m Korsch telescope designed to provide a large field of view. It carries two instruments with a common field-of-view of ~0.54 deg2: the visual imager (VIS) and the near infrared instrument (NISP) which contains a slitless spectrometer and a three bands photometer. The Euclid wide survey will cover 15,000 deg2 of the extragalactic sky and is complemented by two 20 deg2 deep fields. For WL, Euclid measures the shapes of 30-40 resolved galaxies per arcmin2 in one broad visible R+I+Z band (550-920 nm). The photometric redshifts for these galaxies reach a precision of dz/(1+z) \lt 0.05. They are derived from three additional Euclid NIR bands (Y, J, H in the range 0.92-2.0 micron), complemented by ground based photometry in visible bands derived from public data or through engaged collaborations. The BAO are determined from a spectroscopic survey with a redshift accuracy dz/(1+z) =0.001. The slitless spectrometer, with spectral resolution ~250, predominantly detects Ha emission line galaxies. Euclid is a Medium Class mission of the ESA Cosmic Vision 2015-2025 programme, with a foreseen launch date in 2019. This report (also known as the Euclid Red Book) describes the outcome of the Phase A study.