Related papers: Deep Learning for Line Intensity Mapping Observati…
One of the primary goals in spectrum occupancy mapping is to create a system that is robust to assumptions about the number of sensors, occupancy threshold (in dBm), sensor noise, number of emitters and the propagation environment. We show…
Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the…
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…
One of the toughest challenges in modern cosmology is to probe the small scales $k \sim 0.5\,$Mpc$^{-1}$ in the matter power spectrum and clustering. We show that such small scales will be accessible via upcoming line-intensity mapping…
Deep learning has gained great popularity due to its widespread success on many inference problems. We consider the application of deep learning to the sparse linear inverse problem, where one seeks to recover a sparse signal from a few…
Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…
Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the…
Many continuous gravitational wave searches are affected by instrumental spectral lines that could be confused with a continuous astrophysical signal. Several techniques have been developed to limit the effect of these lines by penalising…
Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…
Non-Intrusive Load Monitoring (NILM) is an energy efficiency technique to track electricity consumption of an individual appliance in a household by one aggregated single, such as building level meter readings. The goal of NILM is to…
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are…
Modern deep neural networks (DNNs) become frail when the datasets contain noisy (incorrect) class labels. Robust techniques in the presence of noisy labels can be categorized into two folds: developing noise-robust functions or using…
This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…
We apply a mass reconstruction technique to simulated large-scale structure gravitational distortion maps, from 2.5' to 10 degree scales, for different cosmological scenarii. The projected mass is reconstructed using a non-parametric least…
We address the problem of line confusion in intensity mapping surveys and explore the possibility to mitigate line foreground contamination by progressively masking the brightest pixels in the observed map. We consider experiments targeting…
With the aim of building a data-set of spectral properties of well studied early-type galaxies showing emission lines, we present intermediate resolution spectra of 50 galaxies in the nearby Universe. The sample, which covers several of the…
Gravitational lensing deflects the paths of cosmic infrared background (CIB) photons, leaving a measurable imprint on CIB maps. The resulting statistical anisotropy can be used to reconstruct the matter distribution out to the redshifts of…
The 21 cm intensity mapping provides a promising probe of the large-scale structure. Astrophysical foregrounds, as the main source of contamination to the cosmological 21 cm signal, persist in a wedge-like region of Fourier space due to the…
Dark matter cannot be observed directly, but its weak gravitational lensing slightly distorts the apparent shapes of background galaxies, making weak lensing one of the most promising probes of cosmology. Several observational studies have…
We investigate the prospects of measuring the cosmic magnification effect by cross-correlating neutral hydrogen intensity mapping (HI IM) maps with background optical galaxies. We forecast the signal-to-noise ratio for HI IM data from…