Related papers: Valley notch filter in a graphene strain superlatt…

This paper introduces feature gradient flow, a new technique for interpreting deep learning models in terms of features that are understandable to humans. The gradient flow of a model locally defines nonlinear coordinates in the input data…

The electron transport of different conical valleys is investigated in graphene with extended line-defects. Intriguingly, the electron with a definite incident angle can be completely modulated into one conical valley by a resonator which…

Kelvin probe force microscopy (KPFM) has been employed to probe charge carriers in a graphene/hexagonal boron nitride (hBN) heterostructure [Nano Lett, 21, 5013 (2021)]. We propose an approach for operating valley filtering based on the…

Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best…

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches,…

The use of graph convolution in the development of recommender system algorithms has recently achieved state-of-the-art results in the collaborative filtering task (CF). While it has been demonstrated that the graph convolution operation is…

We consider tunneling transport between two parallel graphene sheets where one is a single-layer sample and the other one a bilayer. In the presence of an in-plane magnetic field, the interplay between combined energy and momentum…

Many works have concentrated on visualizing and understanding the inner mechanism of convolutional neural networks (CNNs) by generating images that activate some specific neurons, which is called deep visualization. However, it is still…

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability. In a trainability study, one aims to discern what…

Machine learning can be a powerful tool to discover new signal types in astronomical data. We here apply it to search for long-duration transient gravitational waves triggered by pulsar glitches, which could yield physical insight into the…

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking…

There is an opportunity for deep learning to revolutionize science and technology by revealing its findings in a human interpretable manner. To do this, we develop a novel data-driven approach for creating a human-machine partnership to…

We derive a method to efficiently compute the Green function of on arbitrary Hamiltonians defined on semi-infinite and periodic quasi-one-dimensional lattices. Computing the Green function is the backbone of quantum transport, electronic…

This work investigates the feasibility of electrical valley filtering for holes in transition metal dichalcogenides. We look specifically into the scheme that utilizes a potential barrier to produce valley-dependent tunneling rates, and…

The interplay of massive electrons with spin-orbit coupling in bulk graphene results in a spin-valley dependent gap. Thus, a barrier with such properties can act as a filter, transmitting only opposite spins from opposite valleys. In this…

The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification. The use of CNNs becomes problematic…

We propose a scheme to trap and filter electrons, valley dependently, on a scale beyond the diffraction limit, in a gapped Dirac system using a circularly polarized light beam and a microscale metallic resonator. The main mechanism allowing…

Graph filters and their inverses have been widely used in denoising, smoothing, sampling, interpolating and learning. Implementation of an inverse filtering procedure on spatially distributed networks (SDNs) is a remarkable challenge, as…

We report on the emergence of bulk, valley-polarized currents in graphene-based devices, driven by spatially varying regions of broken sublattice symmetry, and revealed by non-local resistance ($R_\mathrm{NL}$) fingerprints. By using a…

In the emerging field of mechanical metamaterials, using periodic lattice structures as a primary ingredient is relatively frequent. However, the choice of aperiodic lattices in these structures presents unique advantages regarding failure,…