Related papers: Data-driven estimation of transfer integrals in un…
With the increasing use of nonlinear devices in both generation and consumption of power, it is essential that we develop accurate and quick control for active filters to suppress harmonics. Time delays between input and output are…
We establish a theoretical correspondence between spin-one antiferromagnetic spinor condensates in an external magnetic field and quantum rotor models in an external potential. We show that the rotor model provides a conceptually clear…
Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure…
Accurate modeling of Short Fiber Reinforced Composites (SFRCs) remains computationally expensive for full-field simulations. Data-driven surrogate models using Artificial Neural Networks (ANNs) have been proposed as an efficient alternative…
Conducting altermagnets have recently emerged as intriguing materials supporting strongly spin-polarized currents without magnetic stray fields. We demonstrate that altermagnets enable three key functionalities, merging superconductivity…
Physics-informed Neural Networks (PINNs) have recently gained popularity due to their effective approximation of partial differential equations (PDEs) using deep neural networks (DNNs). However, their out of domain behavior is not well…
Deep learning in k-space has demonstrated great potential for image reconstruction from undersampled k-space data in fast magnetic resonance imaging (MRI). However, existing deep learning-based image reconstruction methods typically apply…
Quantized CNN inference on ultra-low-power MCUs incurs unnecessary computations in neurons that produce saturated output values. These values are too extreme and are eventually clamped to the boundaries allowed by the neuron. Often times,…
Aleatoric uncertainties - irremovable variability in microstructure morphology, constituent behavior, and processing conditions - pose a major challenge to developing uncertainty-robust digital twins. We introduce the Variational Deep…
Neutron scattering experiments have played a crucial role in characterizing the spin and charge correlations in copper-oxide superconductors. While the data are often interpreted with respect to specific theories of the cuprates, an attempt…
For electron-doped cuprates, the strong suppression of antiferromagnetic spin correlation by efficient reduction annealing by the "protect-annealing" method leads to superconductivity not only with lower Ce concentrations but also with…
Monotonic neural networks have recently been proposed as a way to define invertible transformations. These transformations can be combined into powerful autoregressive flows that have been shown to be universal approximators of continuous…
Machine learning has recently been applied to many problems in condensed matter physics. A common point of many proposals is to save computational cost by training the machine with data from a simple example and then using the machine to…
This study focuses on inverting time-domain airborne electromagnetic data in 2D by training a neural-network to understand the relationship between data and conductivity, thereby removing the need for expensive forward modeling during the…
Na5Cu3O6, a new member of one dimensional charge ordered chain cuprates, was synthesized via the azide/nitrate route by reacting NaN3, NaNO3 and CuO. According to single crystal X-ray analysis, one dimensional CuO2 chains built up from…
We propose a method of quantum machine learning called quantum mutual information neural estimation (QMINE) for estimating von Neumann entropy and quantum mutual information, which are fundamental properties in quantum information theory.…
We present here a study of the magnetic properties of the antiferromagnetic dimer material CuVOF$_4$(H$_2$O)$_6\cdot$H$_2$O, in which the dimer unit is composed of two different $S = 1/2$ species, Cu(II) and V(IV). An applied magnetic field…
Inferring transient molecular structural dynamics from diffraction data is an ambiguous task that often requires different approximation methods. In this paper we present an attempt to tackle this problem using machine learning. While most…
We present Photon Splatting, a physics-guided neural surrogate model for real-time wireless channel prediction in complex environments. The proposed framework introduces surface-attached virtual sources, referred to as photons, which carry…
The phenomenon of Anderson localization wherein non-interacting electrons are localized by quenched impurities is a subject matter that has been extremely well studied. However, localization transition under the combined influence of…