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

This work proposes an unsupervised fusion framework based on deep convolutional transform learning. The great learning ability of convolutional filters for data analysis is well acknowledged. The success of convolutive features owes to…

Analogous to charge and spin, electrons in solids endows an additional degree of freedom: the valley pseudospin. Two-dimensional hexagonal materials such as graphene exhibit two valleys, labelled as $\mathbf{K}$ and $\mathbf{K}^{\prime}$.…

Machine learning techniques, notably various deep neural network methods, are instrumental in processing extensive and intricate data sets in engineering and scientific fields. This paper shows how deep neural networks can inversely design…

Based on Green's function formalism, the existence of multiple mobility edges in a one-dimensional magnetic-non-magnetic superlattice geometry in presence of external electric field is predicted, and, it leads to the possibility of getting…

When arranged in a periodic geometry, arrays of metallic nanostructures are capable of supporting collective modes known as lattice resonances. These modes, which originate from the coherent multiple scattering between the elements of the…

Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing models predict saliency using local mechanisms limited to the…

Deep convolutional networks have recently shown excellent performance on Fine-Grained Vehicle Classification. Based on these existing works, we consider that the back-probation algorithm does not focus on extracting less discriminative…

It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning. However, most approaches that explicitly incorporate invariances into a model architecture only make use of very simple…

This paper proposes a new learning paradigm called filter grafting, which aims to improve the representation capability of Deep Neural Networks (DNNs). The motivation is that DNNs have unimportant (invalid) filters (e.g., l1 norm close to…

The valley degeneracy of electron states in graphene stimulates intensive research of valley-related optical and transport phenomena. While many proposals on how to manipulate valley states have been put forward, experimental access to the…

Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given and already trained Deep Neural Net, and a set of test inputs, how can we…

Graph Neural Networks (GNNs) often struggle in preserving high-frequency components of nodal signals when dealing with directed graphs. Such components are crucial for modeling flow dynamics, without which a traditional GNN tends to treat a…

We investigate the optical conductivity, along with longitudinal and transverse conductivities, in buckled hexagonal lattice such as silicene subjected to both an in-plane magnetic field and a perpendicular electric field. In this model, we…

The present paradigm in design and modelling of lattice architected mechanical metamaterials is mostly limited to traditional numerical methods like finite element analysis. Recently, the use of machine learning and artificial intelligence…

We introduce "AnnealSGD", a regularized stochastic gradient descent algorithm motivated by an analysis of the energy landscape of a particular class of deep networks with sparse random weights. The loss function of such networks can be…

We recast the forward pass of a multilayered convolutional neural network (CNN) as the solution to the problem of sparse least squares migration (LSM). The CNN filters and feature maps are shown to be analogous, but not equivalent, to the…

Straintronic devices made of carbon-based materials have been pushed up due to the graphene high mechanical flexibility and the possibility of interesting changes in transport properties. Properly designed strained systems have been…

This work introduces a wavelet neural network to learn a filter-bank specialized to fit non-stationary signals and improve interpretability and performance for digital signal processing. The network uses a wavelet transform as the first…

Gravitational wave science is a pioneering field with rapidly evolving data analysis methodology currently assimilating and inventing deep learning techniques. The bulk of the sophisticated flagship searches of the field rely on the…

Graphene on hBN (G/hBN) has a long period moir\'{e} superstructure owing to the lattice mismatch between two materials. Long periodic potential caused by the moir\'{e} superstructure induces modulation of electronic properties of the…