English
Related papers

Related papers: Using Programmable Graphene Channels as Weights in…

200 papers

We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational…

Machine Learning · Computer Science 2019-11-19 Ferran Alet , Adarsh K. Jeewajee , Maria Bauza , Alberto Rodriguez , Tomas Lozano-Perez , Leslie Pack Kaelbling

Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…

Machine Learning · Computer Science 2023-02-07 Shuai Zhang , Meng Wang , Pin-Yu Chen , Sijia Liu , Songtao Lu , Miao Liu

In wireless networks characterized by dense connectivity, the significant signaling overhead generated by distributed link scheduling algorithms can exacerbate issues like congestion, energy consumption, and radio footprint expansion. To…

Networking and Internet Architecture · Computer Science 2025-09-09 Zhongyuan Zhao , Gunjan Verma , Ananthram Swami , Santiago Segarra

Graphene is an ideal material for spin transport as very long spin relaxation times and lengths can be achieved even at room temperature. However, electrical spin injection is challenging due to the conductivity mismatch problem. Spin…

Mesoscale and Nanoscale Physics · Physics 2018-10-30 D. I. Indolese , S. Zihlmann , P. Makk , C. Jünger , K. Thodkar , C. Schönenberger

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue…

Optimization and Control · Mathematics 2019-02-12 Thu Dinh , Jack Xin

In this work, we present a performance analysis of Field Effect Transistors based on recently fabricated 100% hydrogenated graphene (the so-called graphane) and theoretically predicted semi-hydrogenated graphene (i.e. graphone). The…

Mesoscale and Nanoscale Physics · Physics 2015-05-18 Gianluca Fiori , S. Lebègue , A. Betti , P. Michetti , M. Klintenberg , O. Eriksson , Giuseppe Iannaccone

Graphene, as a material with a small intrinsic spin-orbit interaction of approximately 1 $\mu$eV, has a limited application in spintronics. Adsorption of graphene on the surfaces of heavy-metals was proposed to induce the strong…

Materials Science · Physics 2018-12-27 Elena Voloshina , Yuriy Dedkov

Graphene, the atomically-thin honeycomb carbon lattice, is a highly conducting 2D material whose exposed electronic structure offers an ideal platform for sensing. Its biocompatible, flexible, and chemically inert nature associated to the…

Graph neural networks (GNNs) naturally align with sparse operators and unstructured discretizations, making them a promising paradigm for physics-informed machine learning in computational mechanics. Motivated by discrete physics losses and…

Machine Learning · Computer Science 2026-02-10 Jianchuan Yang , Xi Chen , Jidong Zhao

A popular method of force-directed graph drawing is multidimensional scaling using graph-theoretic distances as input. We present an algorithm to minimize its energy function, known as stress, by using stochastic gradient descent (SGD) to…

Computational Geometry · Computer Science 2018-06-29 Jonathan X. Zheng , Samraat Pawar , Dan F. M. Goodman

Due to the massive parallel computing capability and outstanding image and signal processing performance, cellular neural network (CNN) is one promising type of non-Boolean computing system that can outperform the traditional digital logic…

Emerging Technologies · Computer Science 2016-09-21 Chenyun Pan , Azad Naeemi

Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most existing methods use "graph sampling" or "layer-wise…

Machine Learning · Computer Science 2021-09-03 Ming Chen , Zhewei Wei , Bolin Ding , Yaliang Li , Ye Yuan , Xiaoyong Du , Ji-Rong Wen

Graphene supported on a transition metal dichalcogenide substrate offers a novel platform to study the spin transport in graphene in presence of a substrate induced spin-orbit coupling, while preserving its intrinsic charge transport…

Mesoscale and Nanoscale Physics · Physics 2018-01-24 Siddhartha Omar , Bart J. van Wees

Training Graph Neural Networks (GNNs) on real-world graphs consisting of billions of nodes and edges is quite challenging, primarily due to the substantial memory needed to store the graph and its intermediate node and edge features, and…

Machine Learning · Computer Science 2023-08-08 Kaidi Cao , Rui Deng , Shirley Wu , Edward W Huang , Karthik Subbian , Jure Leskovec

Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model…

Machine Learning · Computer Science 2021-12-22 Fei Sun , Minghai Qin , Tianyun Zhang , Xiaolong Ma , Haoran Li , Junwen Luo , Zihao Zhao , Yen-Kuang Chen , Yuan Xie

Graphene solution-gated field-effect transistors (SGFETs) are a promising platform for the recording of cell action potentials due to the intrinsic high signal amplification of graphene transistors. In addition, graphene technology fulfils…

The current work reports an efficient deep neural network (DNN) accelerator where synaptic weight elements are controlled by ferroelectric domain dynamics. An integrated device-to-algorithm framework for benchmarking novel synaptic devices…

Emerging Technologies · Computer Science 2022-10-14 Sayani Majumdar

Scalable and symmetry-consistent force-field models are essential for extending quantum-accurate simulations to large spatiotemporal scales. While descriptor-based neural networks can incorporate lattice symmetries through carefully…

Strongly Correlated Electrons · Physics 2026-03-03 Yunhao Fan , Gia-Wei Chern

Tailor-made graphene nanostructures can exhibit symmetry-protected topological boundary states that host localized spin-$1/2$ moments. However, one frequently observes charge transfer on coinage metal substrates, which results in spinless…

We present a design-scheme for ultra-low power neuromorphic hardware using emerging spin-devices. We propose device models for 'neuron', based on lateral spin valves and domain wall magnets that can operate at ultra-low terminal voltage of…

Disordered Systems and Neural Networks · Physics 2012-07-19 Mrigank Sharad , Charles Augustine , Georgios Panagopoulos , Kaushik Roy