Related papers: SKYNET: an efficient and robust neural network tra…

With the advent of new spectroscopic surveys from ground and space, observing up to hundreds of millions of galaxies, spectra classification will become overwhelming for standard analysis techniques. To prepare for this challenge, we…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

Modern digital engineering design process commonly involves expensive repeated simulations on varying three-dimensional (3D) geometries. The efficient prediction capability of neural networks (NNs) makes them a suitable surrogate to provide…

Spiking neural networks (SNNs) have received significant attention for their biological plausibility. SNNs theoretically have at least the same computational power as traditional artificial neural networks (ANNs). They possess potential of…

Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we construct a novel dataset called WikiSatNet by…

Traditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time-consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale…

We introduce QuasarNET, a deep convolutional neural network that performs classification and redshift estimation of astrophysical spectra with human-expert accuracy. We pose these two tasks as a \emph{feature detection} problem: presence or…

In recent years, deep learning based object detection methods have achieved promising performance in controlled environments. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges:…

Deep neural networks (DNNs) has shown great promise in computer vision tasks. However, machine vision achieved by DNNs cannot be as robust as human perception. Adversarial attacks and data distribution shifts have been known as two major…

Satellite-derived data products and climate model simulations of geophysical variables like precipitation, often exhibit systematic biases compared to in-situ measurements. Bias correction and spatial downscaling are fundamental components…

The main flaw of neural network ensembling is that it is exceptionally demanding computationally, especially, if the individual sub-models are large neural networks, which must be trained separately. Having in mind that modern DNNs can be…

The era of large-scale astronomical surveys demands innovative approaches for rapid and accurate analysis of extensive spectral data, and a promising direction in which to address this challenge is offered by machine learning. Here, we…

With the volume and availability of astronomical data growing rapidly, astronomers will soon rely on the use of machine learning algorithms in their daily work. This proceeding aims to give an overview of what machine learning is and delve…

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones…

Buildings' segmentation is a fundamental task in the field of earth observation and aerial imagery analysis. Most existing deep learning-based methods in the literature can be applied to a fixed or narrow-range spatial resolution imagery.…

In the low-bit quantization field, training Binary Neural Networks (BNNs) is the extreme solution to ease the deployment of deep models on resource-constrained devices, having the lowest storage cost and significantly cheaper bit-wise…

Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less…

This report presents design considerations for automatically generating satellite imagery datasets for training machine learning models with emphasis placed on dense classification tasks, e.g. semantic segmentation. The implementation…

Deep neural networks have gained tremendous popularity in last few years. They have been applied for the task of classification in almost every domain. Despite the success, deep networks can be incredibly slow to train for even moderate…

Machine learning has rapidly become a tool of choice for the astronomical community. It is being applied across a wide range of wavelengths and problems, from the classification of transients to neural network emulators of cosmological…