Related papers: SPINN: a straightforward machine learning solution…

Pulsars in relativistic binary systems have emerged as fantastic natural laboratories for testing theories of gravity, the most prominent example being the double pulsar, PSR J0737$-$3039. The HTRU-South Low Latitude pulsar survey…

Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for solving Partial Differential Equations (PDEs) by incorporating physical constraints into deep learning models. However, standard PINNs often require a large…

Traditionally, sparse retrieval systems relied on lexical representations to retrieve documents, such as BM25, dominated information retrieval tasks. With the onset of pre-trained transformer models such as BERT, neural sparse retrieval has…

The Parkes Multibeam Pulsar Survey is the most successful survey of the Galactic plane ever performed, finding over 600 pulsars in the initial processing. We report on reprocessing of all 40,000 beams with a number of algorithms, including…

Searching for periodic non-accelerated signals in presence of ideal white noise using the fully phase-coherent Fast Folding Algorithm (FFA) is theoretically established as a more sensitive search method than the Fast Fourier Transform (FFT)…

Variational Physics-Informed Neural Networks (VPINNs) utilize a variational loss function to solve partial differential equations, mirroring Finite Element Analysis techniques. Traditional hp-VPINNs, while effective for high-frequency…

Sparse identification of nonlinear dynamical systems is a topic of continuously increasing significance in the dynamical systems community. Here we explore it at the level of lattice nonlinear dynamical systems of many degrees of freedom.…

In Dai et al. (2016) we developed a formalism for computing variance images from standard, interferometric radio images containing time and frequency information. Variance imaging with future radio continuum surveys allows us to identify…

The simulation of power system dynamics poses a computationally expensive task. Considering the growing uncertainty of generation and demand patterns, thousands of scenarios need to be continuously assessed to ensure the safety of power…

Physically informed neural networks (PINNs) are a promising emerging method for solving differential equations. As in many other deep learning approaches, the choice of PINN design and training protocol requires careful craftsmanship. Here,…

Artificial intelligence has revolutionized optical device design, overcoming the efficiency bottlenecks of traditional methods. For holographic metasurfaces, conventional iterative algorithms suffer from time-consuming iterations and…

In this work, we present a novel sampling-based path planning method, called SPRINT. The method finds solutions for high dimensional path planning problems quickly and robustly. Its efficiency comes from minimizing the number of collision…

The search for pulsars produces a massive amount of data which needs to be processed and analyzed. The limited speed of manual observation necessitates the involvement of large numbers of people to keep up with data collection. This paper…

Physics-informed neural networks (PINN) have recently emerged as a promising application of deep learning in a wide range of engineering and scientific problems based on partial differential equation (PDE) models. However, evidence shows…

The vibrational response of structural components carries valuable information about their underlying mechanical properties, health status and operational conditions. This underscores the need for the development of efficient physics-based…

A method for solving elasticity problems based on separable physics-informed neural networks (SPINN) in conjunction with the deep energy method (DEM) is presented. Numerical experiments have been carried out for a number of problems showing…

In this study, the capabilities of the Physics-Informed Neural Network (PINN) method are investigated for three major tasks: modeling, simulation, and optimization in the context of the heat conduction problem. In the modeling phase, the…

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we…

Currently, the deep neural network is the mainstream for machine learning, and being actively developed for biomedical imaging applications with an increasing emphasis on tomographic reconstruction for MRI, CT, and other imaging modalities.…

We present the search methods and initial results for transient radio signals in the High Time Resolution Universe (HTRU) Survey. The HTRU survey's single-pulse search, the software designed to perform the search, and a determination of the…