Related papers: ABC-SN: Attention Based Classifier for Supernova S…

We present a method for automated classification of galaxies with low signal-to-noise (S/N) spectra typical of redshift surveys. We develop spectral simulations based on the parameters for the 2dF Galaxy Redshift Survey, and with these…

Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing…

Automated techniques have been developed to automate the process of classification of objects or their analysis. The large datasets provided by upcoming spectroscopic surveys with dedicated telescopes urges scientists to use these automated…

Spike train classification has recently become an important topic in the machine learning community, where each spike train is a binary event sequence with \emph{temporal-sparsity of signals of interest} and \emph{temporal-noise}…

Spiking Neural Networks (SNNs) have emerged as an attractive alternative to traditional deep learning frameworks, since they provide higher computational efficiency in event driven neuromorphic hardware. However, the state-of-the-art (SOTA)…

We describe the observing strategy, data reduction tools and early results of a supernova (SN) search project, named SUDARE, conducted with the ESO VST telescope aimed at measuring the rate of the different types of SNe in the redshift…

Upcoming photometric surveys will discover tens of thousands of Type Ia supernovae (SNe Ia), vastly outpacing the capacity of our spectroscopic resources. In order to maximize the science return of these observations in the absence of…

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or…

Deep neural networks have surpassed human performance in key visual challenges such as object recognition, but require a large amount of energy, computation, and memory. In contrast, spiking neural networks (SNNs) have the potential to…

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep…

It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps…

Dramatic raising of Deep Learning (DL) approach and its capability in biomedical applications lead us to explore the advantages of using DL for sleep Apnea-Hypopnea severity classification. To reduce the complexity of clinical diagnosis…

The spectral energy distribution (SED) sequence for type Ia supernovae (SN Ia) is modeled by an artificial neural network. The SN Ia luminosity is characterized as a function of phase, wavelength, a color parameter and a decline rate…

Acoustic Scene Classification (ASC) is one of the core research problems in the field of Computational Sound Scene Analysis. In this work, we present SubSpectralNet, a novel model which captures discriminative features by incorporating…

A novel approach for supervised classification is presented which sits at the intersection of machine learning and dynamical systems theory. At variance with other methodologies that employ ordinary differential equations for classification…

This paper introduces the three-branch Dual Attention-Guided Compact Bilinear CNN (DACB-Net) by focusing on learning from disease-specific regions to enhance accuracy and alignment. A global branch compensates for lost discriminative…

We present the results of spectroscopic observations from the ESSENCE high-redshift supernova (SN) survey during its first four years of operation. This sample includes spectra of all SNe Ia whose light curves were presented by Miknaitis et…

Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have…

Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes particularly challenging when data samples are insufficient,…

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this…