Related papers: Deep Learning for Line Intensity Mapping Observati…

Intensity mapping observations measure galaxy clustering fluctuations from spectral-spatial maps, requiring stable noise properties on large angular scales. We have developed specialized readouts and analysis methods for achieving…

We propose a deep-learning approach based on generative adversarial networks (GANs) to reduce noise in weak lensing mass maps under realistic conditions. We apply image-to-image translation using conditional GANs to the mass map obtained…

Existing deep learning real denoising methods require a large amount of noisy-clean image pairs for supervision. Nonetheless, capturing a real noisy-clean dataset is an unacceptable expensive and cumbersome procedure. To alleviate this…

We study how 21 cm intensity mapping can be used to measure gravitational lensing over a wide range of redshift. This can extend weak lensing measurements to higher redshifts than are accessible with conventional galaxy surveys. We…

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of…

The Cosmic Dawn Intensity Mapper (CDIM) will transform our understanding of the era of reionization when the Universe formed the first stars and galaxies, and UV photons ionized the neutral medium. CDIM goes beyond the capabilities of…

Noise modeling lies in the heart of many image processing tasks. However, existing deep learning methods for noise modeling generally require clean and noisy image pairs for model training; these image pairs are difficult to obtain in many…

Searches and analyses of strong gravitational lenses are challenging due to the rarity and image complexity of these astronomical objects. Next-generation surveys (both ground- and space-based) will provide more opportunities to derive…

Using the 21 cm line, observed all-sky and across the redshift range from 0 to 5, the large scale structure of the Universe can be mapped in three dimensions. This can be accomplished by studying specific intensity with resolution ~ 10 Mpc,…

This work presents a deep-learning approach to estimate atmospheric density profiles for use in planetary entry guidance problems. A long short-term memory (LSTM) neural network is trained to learn the mapping between measurements available…

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

The matter distribution of the Universe can be mapped through the weak gravitational lensing (WL) effect: small distortions of the shapes of distant galaxies, which reflects the inhomogeneity of the cosmic density field. The most dominant…

Line intensity mapping is rapidly gaining prominence as a tool to understand galaxy evolution and cosmology at high redshift. However, the standard power spectrum analysis for these surveys suffers from a tight degeneracy between the…

A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a…

We present a new application of deep learning to reconstruct the cosmic microwave background (CMB) temperature maps from the images of microwave sky, and to use these reconstructed maps to estimate the masses of galaxy clusters. We use a…

Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization…

Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage…

Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weakly supervised learning. A major limitation to the…

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text…

We describe a novel end-to-end approach using Machine Learning to reconstruct the power spectrum of cosmological density perturbations at high redshift from observed quasar spectra. State-of-the-art cosmological simulations of structure…