Related papers: Extracting the X-ray reverberation response functi…
Variable continuum emission from AGN can be used to probe the structure of their accretion disks via reverberation mapping. Assuming a variable, hot inner light source irradiates the surrounding accretion disk, time delays between different…
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…
The obscuring circumnuclear torus of dusty molecular gas is one of the major components of active galactic nuclei (AGN). The torus can be studied by analyzing the time response of its infrared (IR) dust emission to variations in the AGN…
The high cost of acquiring labels is one of the main challenges in deploying supervised machine learning algorithms. Active learning is a promising approach to control the learning process and address the difficulties of data labeling by…
Phytoplankton absorb and scatter light in unique ways, subtly altering the color of water, changes that are often minor for human eyes to detect but can be captured by sensitive ocean color instruments onboard satellites from space.…
Interpreting computations in the visual cortex as learning and inference in a generative model of the environment has received wide support both in neuroscience and cognitive science. However, hierarchical computations, a hallmark of visual…
Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…
We model an accretion disk atmosphere and corona photoionized by a central X-ray continuum source. We calculate the opacity and radiation transfer for an array of disk radii, to obtain the two-dimensional structure of the disk and its X-ray…
The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and…
We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space.…
We develop a machine learning model based on a structured variational autoencoder (VAE) framework to reconstruct and generate neutron star (NS) equations of state (EOS). The VAE consists of an encoder network that maps high-dimensional EOS…
Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…
Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape…
We derive an X-ray luminosity function for active galactic nuclei (AGN) that accounts for the X-ray source counts in the 0.5-2.0 and 2-10 keV energy ranges, the redshift distribution of AGNs in the ROSAT Deep Survey (RDS), as well as the…
The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables. Interpreting its reconstruction process as a nonlinear transformation of samples from the latent posterior distribution, we apply the…
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications. However, their behaviour is not yet fully understood. For example, the questions of when they can provide…
Thermal reverberation in accretion discs of active galactic nuclei is thought to be the reason of the continuum UV/optical time lags seen in these sources. Recently, we studied thermal reverberation of a standard Novikov-Thorne accretion…
The UV/optical and X-ray variability of active galactic nuclei (AGN) have long been expected to be well correlated as a result of the X-ray illumination of the accretion disk. Recent monitoring campaigns of nearby AGN, however, found that…
Active galactic nuclei (AGN) are powerful sources of panchromatic radiation. All AGN emit in X-rays, contributing around $\sim 5-10\%$ of the AGN bolometric luminosity. The X-ray emitting region, popularly known as the corona, is…
Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often identifies images…