Related papers: Using Deep Learning for Robust Classification of F…

Recent advances in deep learning have shown their ability to learn strong feature representations for images. The task of image clustering naturally requires good feature representations to capture the distribution of the data and…

Although fast radio bursts (FRBs) have been an active field in astronomy and cosmology, their origin is still unknown to date. One of the interesting topics is the classification of FRBs, which is closely related to the origin of FRBs.…

Generative thermal design for complex geometries is fundamental in many areas of engineering, yet it faces two main challenges: the high computational cost of high-fidelity simulations and the limitations of conventional generative models.…

The Canadian Hydrogen Intensity Mapping Experiment Fast Radio Burst (CHIME/FRB) project has discovered the most repeating fast radio burst (FRB) sources of any telescope. However, most of the physical conclusions derived from this sample…

According to the number of detected bursts, fast radio bursts (FRBs) can be classified into two categories, i.e., one-off FRBs and repeating ones. We make a statistical comparison of these two categories based on the first FRB catalog of…

Vertebral fractures are a consequence of osteoporosis, with significant health implications for affected patients. Unfortunately, grading their severity using CT exams is hard and subjective, motivating automated grading methods. However,…

Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply…

We present a spectro-temporal analysis of 137 fast radio bursts (FRBs) from the first CHIME/FRB baseband catalog, including 125 one-off bursts and 12 repeat bursts, down to microsecond resolution using the least-squares optimization fitting…

CHIME has now detected 18 repeating fast radio bursts (FRBs). We explore what can be learned about the energy distribution and activity level of the repeaters by fitting realistic FRB population models to the data. For a power-law energy…

In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial…

While Gamma-Ray Burst (GRBs) are clear and distinct observed events, every individual GRB is unique. In fact, GRBs are known for their variable behaviour, and BATSE was already able to discover two categories of GRB from the T90…

The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address…

Deep Learning is considered to be a quite young in the area of machine learning research, found its effectiveness in dealing complex yet high dimensional dataset that includes but limited to images, text and speech etc. with multiple levels…

We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric…

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…

Fast Radio Bursts (FRBs), characterized by strong bursts of radiation intensity at radio wavelengths lasting on the order of a millisecond, have yet to be firmly associated with a family, or families, of astronomical sources. It follows…

Fast radio bursts (FRBs) are millisecond-duration radio flashes of extragalactic origin, with magnetars implicated as viable central engines. Yet their triggering and radiation mechanisms remain unknown. Radio telescopes inevitably record…

The ultimate aim of the study is to explore the inverse design of porous metamaterials using a deep learning-based generative framework. Specifically, we develop a property-variational autoencoder (pVAE), a variational autoencoder (VAE)…

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

The occurrence of vacuum arcs or radio frequency (rf) breakdowns is one of the most prevalent factors limiting the high-gradient performance of normal conducting rf cavities in particle accelerators. In this paper, we search for the…