Related papers: Using Deep Learning for Robust Classification of F…
We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying…
To achieve high-levels of autonomy, modern robots require the ability to detect and recover from anomalies and failures with minimal human supervision. Multi-modal sensor signals could provide more information for such anomaly detection…
Understanding the internal organization of neural networks remains a fundamental challenge in deep learning interpretability. We address this challenge by exploring a novel Sparse Mixture of Experts Variational Autoencoder (SMoE-VAE)…
The classification of Gamma-Ray Bursts has long been an unresolved problem. Early long and short burst classification based on duration is not convincing due to the significant overlap in duration plot, which leads to different views on the…
Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…
Fast Radio Bursts (FRBs) are a powerful and mysterious new class of transient that are luminous enough to be detected at cosmological distances. By associating FRBs to host galaxies, we can measure intrinsic and environmental properties…
In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a…
In this study, we focus on the training process and inference improvements of deep neural networks (DNNs), specifically Autoencoders (AEs) and Variational Autoencoders (VAEs), using Random Fourier Transformation (RFT). We further explore…
The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative…
Fast radio bursts (FRBs) are radio signals that last milliseconds. They originate from cosmological distances and have relatively high dispersion measures (DMs), making them being excellent distance indicators. However, the origins of the…
Fast radio bursts (FRBs) are one of the most exciting new mysteries of astrophysics. Their origin is still unknown, but recent observations seems to link them to Soft Gamma Repeaters and, in particular, to magnetar giant flares (MGFs). The…
Structured variational autoencoders (SVAEs) combine probabilistic graphical model priors on latent variables, deep neural networks to link latent variables to observed data, and structure-exploiting algorithms for approximate posterior…
Fast radio bursts (FRBs) are highly dispersed and probably extragalactic radio flashes with millisecond-duration. Recently, the Canadian Hydrogen Intensity Mapping Experiment (using the CHIME/FRB instrument) has reported detections of 13…
Searching for fleeting radio transients like fast radio bursts (FRBs) with wide-field radio telescopes has become a common challenge in data-intensive science. Conventional algorithms normally cost enormous time to seek candidates by…
Fast Radio Burst (FRB) is an extremely energetic cosmic phenomenon of short duration. Discovered only recently and with its origin still unknown, FRBs have already started to play a significant role in studying the distribution and…
The behaviour of fast radio bursts (FRBs) at radio frequencies <400 MHz is not well understood due to very few detections, with only two known sources detected below 300 MHz. Characterising low-frequency emission of FRBs is vital for…
We focus on the problem of unsupervised cell outlier detection and repair in mixed-type tabular data. Traditional methods are concerned only with detecting which rows in the dataset are outliers. However, identifying which cells are…
We collect 133 Fast Radio Bursts (FRBs), including 110 non-repeating and 23 repeating ones, and systematically investigate their observational properties. To check the frequency dependence of FRB classifications, we define our samples with…
We utilize the Quark-Novae (QN) model for Fast Radio Bursts (FRBs; Ouyed et al. 2021; arXiv:2005.09793) to evaluate its performance in reproducing the distribution and statistical properties of key observations. These include frequency,…
Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…