检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Lin, Mingbao Ji, Rongrong Zhang, Yuxin Zhang, Baochang Wu, Yongjian Tian, Yonghong Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University China School of Automation Science and Electrical Engineering Beihang University China Co. Ltd China School of Electronics Engineering and Computer Science Peking University Beijing China Peng Cheng Laboratory Shenzhen China

Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/ optimization or regularization based on ruleof- thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combinations of pruned structure for deep networks, we first propose to shrink the combinations where the preserved channels are limited to a specific space, thus the combinations of pruned structure can be significantly reduced. And then, we formulate the search of optimal pruned structure as an optimization problem and integrate the ABC algorithm to solve it in an automatic manner to lessen human interference. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner. Experiments on CIFAR-10 show that ABCPruner reduces 73.68% of FLOPs and 88.68% of parameters with even 0.06% accuracy improvement for VGGNet-16. On ILSVRC-2012, it achieves a reduction of 62.87% FLOPs and removes 60.01% of parameters with negligible accuracy cost for ResNet-152. The source codes can be available at https://***/lmbxmu/ABCPruner. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Vector Symbolic Architectures as a computing Framework for Emerging Hardware

arXiv

引用

arXiv 2021年

作者： Kleyko, Denis Davies, Mike Frady, E. Paxon Kanerva, Pentti Kent, Spencer J. Olshausen, Bruno A. Osipov, Evgeny Rabaey, Jan M. Rachkovskij, Dmitri A. Rahimi, Abbas Sommer, Friedrich T. The Redwood Center for Theoretical Neuroscience The University of California BerkeleyCA94720 United States The Intelligent Systems Lab Research Institutes of Sweden Kista16440 Sweden The Neuromorphic Computing Laboratory Intel Labs Santa ClaraCA95054 United States The Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå97187 Sweden The Department of Electrical Engineering and Computer Sciences The University of California BerkeleyCA94720 United States International Research and Training Center for Information Technologies and Systems Kyiv03680 Ukraine IBM Research – Zurich Rüschlikon8803 Switzerland

This article reviews recent progress in the development of the computing framework Vector Symbolic Architectures (also known as Hyperdimensional computing). This framework is well suited for implementation in stochastic, emerging hardware and it naturally expresses the types of cognitive operations required for Artificial Intelligence (AI). We demonstrate in this article that the field-like algebraic structure of Vector Symbolic Architectures offers simple but powerful operations on high-dimensional vectors that can support all data structures and manipulations relevant to modern computing. In addition, we illustrate the distinguishing feature of Vector Symbolic Architectures, "computing in superposition," which sets it apart from conventional computing. It also opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. We sketch ways of demonstrating that Vector Symbolic Architectures are computationally universal. We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware. This article serves as a reference for computer architects by illustrating the philosophy behind Vector Symbolic Architectures, techniques of distributed computing with them, and their relevance to emerging computing hardware, such as neuromorphic computing. Copyright © 2021, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Optimizing for periodicity: a model-independent approach to flux crosstalk calibration for superconducting circuits

arXiv

引用

arXiv 2022年

作者： Dai, X. Trappen, R. Yang, R. Disseler, S.M. Basham, J.I. Gibson, J. Melville, A.J. Niedzielski, B.M. Das, R. Kim, D.K. Yoder, J.L. Weber, S.J. Hirjibehedin, C.F. Lidar, D.A. Lupascu, A. Institute for Quantum Computing Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada Lincoln Laboratory Massachusetts Institute of Technology LexingtonMA02421 United States Department of Physics and Astronomy Dartmouth College HanoverNH03755 United States Departments of Electrical & Computer Engineering Chemistry and Physics Center for Quantum Information Science & Technology University of Southern California Los AngelesCA90089 United States Waterloo Institute for Nanotechnology University of Waterloo WaterlooONN2L 3G1 Canada

Flux tunability is an important engineering resource for superconducting circuits. Large-scale quantum computers based on flux-tunable superconducting circuits face the problem of flux crosstalk, which needs to be accurately calibrated to realize high-fidelity quantum operations. Typical calibration methods either assume that circuit elements can be effectively decoupled and simple models can be applied, or require a large amount of data. Such methods become ineffective as the system size increases and circuit interactions become stronger. Here we propose a new method for calibrating flux crosstalk, which is independent of the underlying circuit model. Using the fundamental property that superconducting circuits respond periodically to external fluxes, crosstalk calibration of N flux channels can be treated as N independent optimization problems, with the objective functions being the periodicity of a measured signal depending on the compensation parameters. We demonstrate this method on a small-scale quantum annealing circuit based on superconducting flux qubits, achieving comparable accuracy with previous methods. We also show that the objective function usually has a nearly convex landscape, allowing efficient optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Generating Approximate Ground States of Molecules Using Quantum Machine Learning

arXiv

引用

arXiv 2022年

作者： Ceroni, Jack Stetina, Torin F. Kieferová, Mária Marrero, Carlos Ortiz Arrazola, Juan Miguel Wiebe, Nathan Xanadu TorontoONM5G 2C8 Canada Department of Mathematics University of Toronto TorontoONM5S 3E1 Canada Simons Institute for the Theory of Computing BerkeleyCA94704 United States Berkeley Quantum Information and Computation Center University of California BerkeleyCA94720 United States Centre for Quantum Computation and Communication Technology Centre for Quantum Software and Information University of Technology SydneyNSW2007 Australia AI & Data Analytics Division Pacific Northwest National Laboratory RichlandWA99354 United States Department of Electrical & Computer Engineering North Carolina State University RaleighNC27607 United States Department of Computer Science University of Toronto ONM5S 1A1 Canada High Performance Computing Group Pacific Northwest National Laboratory RichlandWA99354 United States

The potential energy surface (PES) of molecules with respect to their nuclear positions is a primary tool in understanding chemical reactions from first principles. However, obtaining this information is complicated by the fact that sampling a large number of ground states over a high-dimensional PES can require a vast number of state preparations. In this work, we propose using a generative quantum machine learning model to prepare quantum states at arbitrary points on the PES. The model is trained using quantum data consisting of ground-state wavefunctions associated with different classical nuclear coordinates. Our approach uses a classical neural network to convert the nuclear coordinates of a molecule into quantum parameters of a variational quantum circuit. The model is trained using a fidelity loss function to optimize the neural network parameters. We show that gradient evaluation is efficient and numerically demonstrate our method’s ability to prepare wavefunctions on the PES of hydrogen chains, water, and beryllium hydride. In all cases, we find that a small number of training points are needed to achieve very high overlap with the groundstates in practice. From a theoretical perspective, we further prove limitations on these protocols by showing that if we were able to learn across an avoided crossing using a small number of samples, then we would be able to violate Grover’s lower bound. Additionally, we prove lower bounds on the amount of quantum data needed to learn a locally optimal neural network function using arguments from quantum Fisher information. This work further identifies that quantum chemistry can be an important use case for quantum machine learning. © 2022, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

FAIR for AI: An interdisciplinary and international community building perspective

arXiv

引用

arXiv 2022年

作者： Huerta, E.A. Blaiszik, Ben Brinson, L. Catherine Bouchard, Kristofer E. Diaz, Daniel Doglioni, Caterina Duarte, Javier M. Emani, Murali Foster, Ian Fox, Geoffrey Harris, Philip Heinrich, Lukas Jha, Shantenu Katz, Daniel S. Kindratenko, Volodymyr Kirkpatrick, Christine R. Lassila-Perini, Kati Madduri, Ravi K. Neubauer, Mark S. Psomopoulos, Fotis E. Roy, Avik Rübel, Oliver Zhao, Zhizhen Zhu, Ruike Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science University of Chicago ChicagoIL60637 United States Globus University of Chicago ChicagoIL60637 United States Department of Mechanical Engineering and Materials Science Duke University DurhamNC27708 United States Scientific Data Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Biological Systems & Engineering Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Helen Wills Neuroscience Institute University of California Berkeley BerkeleyCA94720 United States Department of Physics University of California La Jolla San DiegoCA92093 United States Lund University Department of Physics Box 118 Lund221 00 Sweden School of Physics & Astronomy The University of Manchester ManchesterM13 9PL United Kingdom Leadership Computing Facility Argonne National Laboratory LemontIL60439 United States Biocomplexity Institute Department of Computer Science University of Virginia CharlottesvilleVA22904 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Technical University Munich Arcisstraße 21 München80333 Germany Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States Electrical and Computer Engineering Rutgers The State University of New Jersey PiscatawayNJ08854 United States National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Electrical & Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States School of Information Sciences University of Illinois at Urbana-Champaign UrbanaIL61801 United States San Diego Supercomputer Center University of California La Jolla San DiegoCA

A foundational set of findable, accessible, interoperable, and reusable (FAIR) principles were proposed in 2016 as prerequisites for proper data management and stewardship, with the goal of enabling the reusability of scholarly data. The principles were also meant to apply to other digital assets, at a high level, and over time, the FAIR guiding principles have been reinterpreted or extended to include the software, tools, algorithms, and workflows that produce data. FAIR principles are now being adapted in the context of AI models and datasets. Here, we present the perspectives, vision, and experiences of researchers from different countries, disciplines, and backgrounds who are leading the definition and adoption of FAIR principles in their communities of practice, and discuss outcomes that may result from pursuing and incentivizing FAIR AI research. The material for this report builds on the FAIR for AI Workshop held at Argonne National laboratory on June 7, 2022. Copyright © 2022, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraint

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Yuan, Zhenlong Yang, Zhidong Cai, Yujun Wu, Kuangxin Liu, Mufan Zhang, Dapeng Jiang, Hao Li, Zhaoxin Wang, Zhaoqi Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China School of Electrical Engineering and Computer Science Australia Hunan Police Academy Information Technology Department Changsha410100 China Shanghai Jiao Tong University Cooperative MediaNet Innovation Center Shanghai200240 China Lanzhou University DSLAB School of Information Science and Engineering 730000 China Ministry of Agriculture and Rural Affairs Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data 100081 China

Recently, patch-deformation methods have exhibited significant effectiveness in multi-view stereo owing to the deformable and expandable patches in reconstructing textureless areas. However, existing approaches neglect to address the problem of deformation instability caused by easily overlooked edge-skipping, potentially leading to matching distortions, thus leaving room for further improvement. To fill this gap, we propose SED-MVS, which adopts panoptic segmentation and multi-trajectory diffusion strategy for segmentation-driven and edge-aligned patch deformation. Specifically, to prevent unanticipated edge-skipping, we first employ SAM2 for panoptic segmentation as depth-edge guidance to guide patch deformation, followed by multi-trajectory diffusion strategy to ensure patches are comprehensively aligned with depth edges. Moreover, to avoid potential inaccuracy of random initialization, we combine both sparse points from LoFTR and monocular depth map from DepthAnything V2 to restore reliable and realistic depth map for initialization and supervised guidance. Finally, we integrate the segmentation image with the monocular depth map to exploit inter-instance occlusion relationship, then further regard them as occlusion map to implement two distinct edge constraint, thereby facilitating occlusion-aware patch deformation. Extensive results on ETH3D, Tanks & Temples, BlendedMVS, Strecha and DL3DV-10K datasets validate the state-of-the-art performance and robust generalization capability of our proposed method. © 1991-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multistage model for robust face alignment using deep neural networks

arXiv

引用

arXiv 2020年

作者： Wang, Huabin Cheng, Rui Zhou, Jian Tao, Liang Kwan, Hon Keung MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei Anhui230601 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada

An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Protein structured reservoir computing for spike-based pattern recognition

arXiv

引用

arXiv 2020年

作者： Tsakalos, Karolos-Alexandros Sirakoulis, Georgios Ch. Adamatzky, Andrew Smith, Jim Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece Unconventional Computing Laboratory University of the West of England BristolBS16 1QY United Kingdom Computer Science Research Centre University of the West of England Xanthi Greece

Nowadays we witness a miniaturisation trend in the semiconductor industry backed up by groundbreaking discoveries and designs in nanoscale characterisation and fabrication. To facilitate the trend and produce ever smaller, faster and cheaper computing devices, the size of nanoelectronic devices is now reaching the scale of atoms or molecules - a technical goal undoubtedly demanding for novel devices. Following the trend, we explore an unconventional route of implementing reservoir computing on a single protein molecule and introduce neuromorphic connectivity with a small-world networking property. We have chosen Izhikevich spiking neurons as elementary processors, corresponding to the atoms of verotoxin protein, and its molecule as a 'hardware' architecture of the communication networks connecting the processors. We apply on a single readout layer, various training methods in a supervised fashion to investigate whether the molecular structured Reservoir computing (RC) system is capable to deal with machine learning benchmarks. We start with the Remote Supervised Method, based on Spike-Timing-Dependent-Plasticity, and carry on with linear regression and scaled conjugate gradient back-propagation training methods. The RC network is evaluated as a proof-of-concept on the handwritten digit images from the standard MNIST and the extended MNIST datasets and demonstrates acceptable classification accuracies in comparison with other similar approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Quantum engineering with hybrid magnonics systems and materials

arXiv

引用

arXiv 2021年

作者： Awschalom, D.D. Du, C.H.R. He, R. Heremans, F.J. Hoffmann, A. Hou, J.T. Kurebayashi, H. Li, Y. Liu, L. Novosad, V. Sklenar, J. Sullivan, S.E. Sun, D. Tang, H. Tiberkevich, V. Trevillian, C. Tsen, A.W. Weiss, L.R. Zhang, W. Zhang, X. Zhao, L. Zollitsch, C.W. Pritzker School of Molecular Engineering University of Chicago ChicagoIL United States Materials Science Division Center for Molecular Engineering Argonne National Laboratory LemontIL United States Department of Physics University of California San Diego San DiegoCA92093 United States Department of Electrical and Computer Engineering Texas Tech University LubbockTX79409 United States Materials Research Laboratory Department of Materials Science and Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States London Centre for Nanotechnology University College London 17-19 Gordon Street LondonWCH1 0AH United Kingdom Materials Science Division Argonne National Laboratory LemontIL United States Department of Physics and Astronomy Wayne State University DetroitMI48201 United States Department of Physics North Carolina State University RaleighNC27695 United States Department of Electrical Engineering Yale University New HavenCT United States Department of Physics Oakland University MI48309 United States Institute for Quantum Computing Department of Chemistry University of Waterloo WaterlooON Canada Center for Nanoscale Materials Argonne National Laboratory LemontIL United States Department of Physics University of Michigan Ann ArborMI48109 United States

Quantum technology has made tremendous strides over the past two decades with remarkable advances in materials engineering, circuit design and dynamic operation. In particular, the integration of different quantum modules has benefited from hybrid quantum systems, which provide an important pathway for harnessing the different natural advantages of complementary quantum systems and for engineering new functionalities. This review focuses on the current frontiers with respect to utilizing magnetic excitatons or magnons for novel quantum functionality. Magnons are the fundamental excitations of magnetically ordered solid-state materials and provide great tunability and flexibility for interacting with various quantum modules for integration in diverse quantum systems. The concomitant rich variety of physics and material selections enable exploration of novel quantum phenomena in materials science and engineering. In addition, the relative ease of generating strong coupling and forming hybrid dynamic systems with other excitations makes hybrid magnonics a unique platform for quantum engineering. We start our discussion with circuit-based hybrid magnonic systems, which are coupled with microwave photons and acoustic phonons. Subsequently, we are focusing on the recent progress of magnon-magnon coupling within confined magnetic systems. Next we highlight new opportunities for understanding the interactions between magnons and nitrogen-vacancy centers for quantum sensing and implementing quantum interconnects. Lastly, we focus on the spin excitations and magnon spectra of novel quantum materials investigated with advanced optical characterization. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Crosslink-net: Double-branch encoder segmentation network via fusing vertical and horizontal convolutions

arXiv

引用

arXiv 2021年

作者： Yu, Qian Qi, Lei Zhou, Luping Wang, Lei Yin, Yilong Shi, Yinghuan Wang, Wuzhang Gao, Yang School of Data and Computer Science Shandong Women's University Jinan250300 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing211189 China The School of Electrical and Information Engineering University of Sydney NSW2006 Australia The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia The School of Soft Shandong University Jinan250100 China Department of Respiratory and Critical Care Medicine Shandong Chest Hospital Jinan250013 China

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://***/Qianyu1226/*** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：