检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Xu, Minrui Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Jamalipour, Abbas Kim, Dong In Shen, Xuemin Leung, Victor C.M. Poor, H. Vincent The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States The Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada The College of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China The Department of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Artificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. This survey paper focuses on the deployment of AIGC applications, e.g., ChatGPT and Dall-E, at mobile edge networks, namely mobile AIGC networks, that provide personalized and customized AIGC services in real time while maintaining user privacy. We begin by introducing the background and fundamentals of generative models and the lifecycle of AIGC services at mobile AIGC networks, which includes data collection, training, fine-tuning, inference, and product management. We then discuss the collaborative cloud-edge-mobile infrastructure and technologies required to support AIGC services and enable users to access AIGC at mobile edge networks. Furthermore, we explore AIGC-driven creative applications and use cases for mobile AIGC networks. Additionally, we discuss the implementation, security, and privacy challenges of deploying mobile AIGC networks. Finally, we highlight some future research directions and open issues for the full realization of mobile AIGC networks. © 2023, CC BY.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

arXiv

引用

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Electronic system for Control of a Thermally Actuated Alignment Device

Electronic System for Control of a Thermally Actuated Alignm...

引用

2010 IEEE International Conference on Industrial Technology (ICIT 2010)

作者： Ruimin. Yang Jeroen van Schieveen Stoyan Nihtianov Jo W. Spronck Delft University of Technology Faculty of Electrical Engineering Department of Microelectronics Electronic Instrumentation Laboratory Mekelweg 4 2628 CD Delft The Netherlands Delft University of Technology Faculty of 3mE Department of Precision and Microsystem Engineering Mechatronic System Design Mekelweg 2 2628 CD Delft The Netherlands

ISBN: (纸本)9781424456956

This article presents the design of an electronic system that is used to control a thermally actuated alignment device. This device is ideal for aligning critical parts in complex, high-precision systems, like, for example, optical elements or the electrodes of capacitive sensors. Accurate temperature control of the thermal elements improves the performance of the alignment in terms of positioning accuracy and operating speed. Furthermore, the article presents the realized test setup and the initial measurement results. The measurement results show the benefits of the new controller.

关键词： Thermal actuation thermal stepper auto-aligment electronic control system smart sensor

来源：评论

学校读者我要写书评

暂无评论

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model

arXiv

引用

arXiv 2024年

作者： Yang, Jichang Chen, Hegan Chen, Jia Wang, Songqi Wang, Shaocong Yu, Yifei Chen, Xi Wang, Bo Zhang, Xinyuan Cui, Binbin Li, Yi Lin, Ning Xu, Meng Li, Yi Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Zhang, Xumeng Shang, Dashan Wang, Han Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering the University of Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China Institute of the Mind the University of Hong Kong Hong Kong University of Chinese Academy of Sciences Beijing100049 China School of Integrated Circuits Hubei Key Laboratory for Advanced Memories Huazhong University of Science and Technology Wuhan430074 China Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong

Human brains image complicated scenes when reading a novel. Replicating this imagination is one of the ultimate goals of AI-Generated Content (AIGC). However, current AIGC methods, such as score-based diffusion, are still deficient in terms of rapidity and efficiency. This deficiency is rooted in the difference between the brain and digital computers. Digital computers have physically separated storage and processing units, resulting in frequent data transfers during iterative calculations, incurring large time and energy overheads. This issue is further intensified by the conversion of inherently continuous and analog generation dynamics, which can be formulated by neural differential equations, into discrete and digital operations. Inspired by the brain, we propose a time-continuous and analog in-memory neural differential equation solver for score-based diffusion, employing emerging resistive memory. The integration of storage and computation within resistive memory synapses surmount the von Neumann bottleneck, benefiting the generative speed and energy efficiency. The closed-loop feedback integrator is time-continuous, analog, and compact, physically implementing an infinite-depth neural network. Moreover, the software-hardware co-design is intrinsically robust to analog noise. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros. Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64.8 and 156.5, respectively. Moreover, it accomplished reductions in energy consumption by factors of 5.2 and 4.1. Our approach heralds a new horizon for hardware solutions in edge computing for generative AI applications. © 2024, CC BY-NC-SA.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver

arXiv

引用

arXiv 2024年

作者： Chen, Hegan Yang, Jichang Chen, Jia Wang, Songqi Wang, Shaocong Wang, Dingchen Tian, Xinyu Yu, Yifei Chen, Xi Lin, Yinan He, Yangu Wu, Xiaoshan Li, Yi Zhang, Xinyuan Lin, Ning Xu, Meng Li, Yi Zhang, Xumeng Wang, Zhongrui Wang, Han Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Institute of the Mind The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China University of Chinese Academy of Sciences Beijing100049 China School of Integrated Circuits Hubei Key Laboratory for Advanced Memories Huazhong University of Science and Technology Wuhan430074 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Digital twins, the cornerstone of Industry 4.0, replicate real-world entities through computer models, revolutionising fields such as manufacturing management and industrial automation. Recent advances in machine learning provide data-driven methods for developing digital twins using discrete-time data and finite-depth models on digital computers. However, this approach fails to capture the underlying continuous dynamics and struggles with modelling complex system behaviour. Additionally, the architecture of digital computers, with separate storage and processing units, necessitates frequent data transfers and Analogue-Digital (A/D) conversion, thereby significantly increasing both time and energy costs. Here, we introduce a memristive neural ordinary differential equation (ODE) solver for digital twins, which is capable of capturing continuous-time dynamics and facilitates the modelling of complex systems using an infinite-depth model. By integrating storage and computation within analogue memristor arrays, we circumvent the von Neumann bottleneck, thus enhancing both speed and energy efficiency. We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4.2-fold projected speedup and a 41.4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin. Additionally, we demonstrate scalability through experimentally grounded simulations of Lorenz96 dynamics, exhibiting projected performance improvements of 12.6-fold in speed and 189.7-fold in energy efficiency relative to traditional digital approaches. By harnessing the capabilities of fully analogue computing, our breakthrough accelerates the development of digital twins, offering an efficient and rapid solution to meet the demands of Industry 4.0. © 2024, CC BY-NC-SA.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Annual business and news:: Beginning the 31st year of the Journal of Guidance, Control, and Dynamics

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2008年第1期31卷 1-1页

作者： Schmidt, George T. Aeronautics and Astronautics Massachusetts Institute of Technology (MIT) AIAA Institute of Electrical and Electronics Engineers Russian Federation Academy of Navigation and Motion Control Department of Mechanical and Aerospace Engineering and Engineering Mechanics University of Missouri-Rolla(UMR) Lockheed Electronics Company Center for Space Research University of Texas Austin United States Wright Laboratory Eglin Air Force Base UMR AIAA Guidance Navigation and Control Technical Committee American Automatic Control Council Lockheed Martin Aeronautics Company Palmdale CA United States C4ISR and Unmanned Air Vehicle (UAV) Programs for Air Vehicle Sciences and Systems Accreditation Board Engineering and Technology Inc./Aeronautical National Technical Committee on Guidance Navigation and Control Department of Mechanical and Aerospace Engineering University at Buffalo State University of New York (SUNY) AIAA Technical Committee on GN and C Air Vehicles Directorate Air Force Research Laboratory (AFRL) Wright-Patterson Air Force Base Space Access and Hypersonic Vehicle Guidance and Control Group Control Science Center of Excellence AFRL AIAA Technical Committee on Guidance Navigation and Control Department of Mechanical and Aeronautical Engineering University of California (UC) Davis United States Boeing Company Modernized Flight Control System for the Apache Longbow AIAA Institute of Electrical and Electronics Engineers AHS Jet Propulsion Laboratory California Institute of Technology Boeing Company Flight Sciences and Advanced Design Group Guidance Navigation and Control (GN and C) Systems Engineer Distributed Space Systems NASA Goddard Space Flight Center (GSFC) AIAA GN and C Technical Committee Department of Aerospace Engineering and Engineering Mechanics University of Texas Austin United States Institute of Navigation American Astronautical Society AIAA Guidance Navigation (GN and C) and Control Technical Committee Department of Aerospace Engineering Iowa State University Iowa

来源：评论

学校读者我要写书评

暂无评论

Random resistive memory-based deep extreme point learning machine for unified visual processing

arXiv

引用

arXiv 2023年

作者： Wang, Shaocong Gao, Yizhao Li, Yi Zhang, Woyu Yu, Yifei Wang, Bo Lin, Ning Chen, Hegan Zhang, Yue Jiang, Yang Wang, Dingchen Chen, Jia Dai, Peng Jiang, Hao Lin, Peng Zhang, Xumeng Qi, Xiaojuan Xu, Xiaoxin So, Hayden Wang, Zhongrui Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China ACCESS - AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong University of Chinese Academy of Sciences Beijing100049 China Frontier Institute of Chip and System Fudan University Shanghai200433 China College of Computer Science and Technology Zhejiang University Zhejiang310027 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent machines is crucial for numerous emerging edge applications, such as augmented and virtual reality and unmanned aerial vehicles, which necessitates unified data representation, unprecedented hardware energy efficiency and rapid model training. However, multi-sensory data are intrinsically heterogeneous, causing significant complexity in the system development for edge-side intelligent machines. In addition, the performance of conventional digital hardware is limited by the physically separated processing and memory units, known as the von Neumann bottleneck, and the physical limit of transistor scaling, which contributes to the slowdown of Moore's law. These limitations are further intensified by the tedious training of models with ever-increasing sizes. In this study, we propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM), that offers efficient unified point set analysis. Data-wise, the multi-sensory data are unified as point sets and can be processed universally. Software-wise, most weights of deep extreme point learning machines are exempted from training, which significantly reduce training complexity. Hardware-wise, nanoscale resistive memory not only enables collocation of memory and processing, mitigating the von Neumann bottleneck and the slowdown of Moore's law, but also leverages the inherent programming stochasticity for generating the random and sparse weights of the DEPLM, which also lessens the impact of read noise. We demonstrate the system's versatility across various data modalities and two different learning tasks. Compared to a conventional digital hardware-based system, our co-design system achieves 5.90×, 21.04×, and 15.79× energy efficiency improv

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Affordability, logistics R&D and fleet systems

引用

NAVAL ENGINEERS JOURNAL 1996年第3期108卷 199-213页

作者： Schulte, DP Skolnick, A He has supported the development and operation of several naval systems including advanced component selection for Trident II fire control and navigation systems. He served as branch manager of the Surface Ship ASW Combat System Branch which acted as the acquisition engineering agent for the AN/SQQ-89 Surface Ship Anti-Submarine Warfare Weapon System. He was then selected to manage the Module Engineering Department which provided engineering support to numerous naval systems including the AN/BSY-1 Submarine Combat System and the Trident II fire control and navigation system. He then served as the deputy program manager for NAVSEA Progressive Maintenance (2M/ATE). He holds a B.S. degree in Electrical Engineering from Purdue University and currently is pursuing a Maste's degree in Public Environmental Affairs at Indiana University—Purdue University Indianapolis. He served at Applied Physics Laboratory/The Johns Hopkins University in missile development then aboard USS Boston (CAG-1) and played leading roles in several weapon system developments (Regulus Terrier Tartar Talos) inertial navigation (Polaris) deep submergence (DSRV) and advanced ship designs (SES). He later was director Combat System Integration Naval Sea Systems Command and head Combat Projects Naval Ship Engineering Center. He led the Navy's High Energy Lasers and Directed Energy Weapons development efforts. He was vice president advanced technology at Operations Research Inc. and vice president maritime engineering at Defense Group Inc. before starting SSC in 1991. Dr. Skolnick holds a B.S. degree in Mathematics and Economics Queens College an M.A. degree in Mathematics and Philosophy Columbia University an M.S. degree in Electrical/Aeronautical Engineering U.S. Naval Postgraduate School and a Ph.D. in Electrical Engineering and Applied Mathematics from Polytechnic University in New York. He is the author of many published papers on engineering design issues source selection procedures and large-scale complex technology problems

The Fleet continues to require high performance systems that can operate with dependability in the seas' unforgiving environments and under hostile action. Those demands are not new. What has changed is the urgent priority formerly assigned to national defense issues. The arguments for continued superpower military strength are now roiled in politics along with unsettled budgets and uncertain force level projections. Current expectations revolve about indefinite fiscal and operational issues (difficult funding constraints and broadband threats). In the actual event of ''doing more with less,'' a practical response is to apply the creative power available from sound engineering judgement and the crucible of experience to the immediate needs of the Fleet. The attempt to shorten the path between advanced development effort and Fleet use has been tried occasionally in the past, often, without exemplary results. The Sustainable Hardware and Affordable Readiness Practices (SHARP) program, is a generic R&D effort under OpNav sponsorship that has been working steadily on sensible solutions to product engineering problems. Armed today with fast-time, large-scale computation abilities and modern tools for technical problem solving coupled with specialized engineering knowledge, it has been refreshed and is underway satisfying existing Fleet needs. The relationship between fully responsive engineering services and current operational needs is always demanding. The connection between advanced engineering development (6.3 category funds) and immediate Fleet usage brings added complexity and challenge, both technical and organizational. Illustrative examples of affordable engineering solutions to ''retain, revise, replace or retire'' questions are presented within the context of both Fleet realities and budgetary limitations. The discussion covers legacy system support, civil/military considerations and Fleet maintenance issues. It describes the substantial and critical payoffs i

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

High Conductance Margin for Efficient Neuromorphic Computing Enabled by Stacking Nonvolatile van der Waals Transistors

引用

Physical Review Applied 2021年第4期16卷 044049-044049页

作者： Liping Xu (徐丽萍) Hao Xiong (熊浩) Zhichao Fu (付志超) Menghan Deng (邓梦晗) Shuiyuan Wang (王水源) Jinzhong Zhang (张金中) Liyan Shang (商丽燕) Kai Jiang (姜凯) Yawei Li (李亚巍) Liangqing Zhu (朱亮清) Liang He Zhigao Hu (胡志高) Junhao Chu (褚君浩) Technical Center for Multifunctional Magneto-Optical Spectroscopy (Shanghai) Engineering Research Center of Nanophotonics & Advanced Instrument (Ministry of Education) Department of Materials School of Physics and Electronic Science East China Normal University Shanghai 200241 China Center for Advanced Electronic Materials and Devices School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Computer Science and Technology East China Normal University Shanghai 200062 China ASIC & System State Key Laboratory School of Microelectronics Fudan University Shanghai 200433 China Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan Shanxi 030006 China Shanghai Institute of Intelligent Electronics & Systems Fudan University Shanghai 200433 China

High-performance artificial synaptic devices are key building blocks for developing efficient neuromorphic computing systems. However, the nonlinear and asymmetric weight update of existing devices has restricted their practical applications. Herein, floating gate nonvolatile memory (FG NVM) devices based on two-dimensional (2D) HfS2/h-BN/FG-graphene heterostructures have been designed and investigated as multifunctional NVM and artificial optoelectronic synapses. Benefiting from the FG architecture, the HfS2-based NVM device exhibits competitive performances, such as a high on:off ratio (>105), large memory window (approximately 100 V), excellent charge retention ability (>104s), and robust durability (>103 cycles). Notably, the artificial optoelectronic synapses based on HfS2 FG NVM show an impressive large conductance margin and good linearity, owing to the ultrahigh photoresponsivity and photogain of HfS2. The energy consumption of per spike in our artificial synapse is as low as 0.2 pJ. Therefore, a high recognition accuracy up to 91.5% of the artificial neural network on the basis of our HfS2-based optoelectronic synapse at the system level has been achieved, which is superior to other reported 2D artificial optoelectronic synapses. This work paves the way forward for all 2D material-based memory for developing efficient optogenetics-inspired neuromorphic computing in brain-inspired intelligent systems.

关键词： electrical conductivity Optoelectronics Synapses 2-dimensional systems Artificial neural networks Transistors Transition metal dichalcogenides Lithography

来源：评论

学校读者我要写书评

暂无评论

Pruning random resistive memory for optimizing analogue AI

arXiv

引用

arXiv 2023年

作者： Li, Yi Wang, Songqi Zhao, Yaping Wang, Shaocong Zhang, Woyu He, Yangu Lin, Ning Cui, Binbin Chen, Xi Zhang, Shiming Jiang, Hao Lin, Peng Zhang, Xumeng Qi, Xiaojuan Wang, Zhongrui Xu, Xiaoxin Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong State Key Lab of Fabrication Technologies for Integrated Circuits Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China Frontier Institute of Chip and System Fudan University Shanghai200433 China College of Computer Science and Technology Zhejiang University Zhejiang310027 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong University of Chinese Academy of Sciences Beijing100049 China Institute of Mind The University of Hong Kong Hong Kong

The rapid advancement of artificial intelligence (AI) has been marked by the large language models exhibiting human-like intelligence. However, these models also present unprecedented challenges to energy consumption and environmental sustainability, which are exacerbated by the increasing number of users and the development of even larger models. One promising solution is to revisit analogue computing, a technique that predates digital computing and exploits emerging analogue electronic devices, such as resistive memory, which features in-memory computing, high scalability, and nonvolatility that addresses the von Neumann bottleneck, slowdown of Moore’s law, and volatile DRAM of conventional digital hardware. However, analogue computing still faces the same challenges as before: programming nonidealities and expensive programming due to the underlying devices physics. Therefore, leveraging the efficiency advantage while mitigating the programming disadvantage of analogue computing with resistive memory is a major open problem in AI hardware and electronics communities. Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network. Software-wise, the topology of a randomly weighted neural network is optimized by pruning connections rather than precisely tuning resistive memory weights. Hardware-wise, we reveal the physical origin of the programming stochasticity using transmission electron microscopy, which is leveraged for large-scale and low-cost implementation of an overparameterized random neural network containing high-performance sub-networks. We implemented the co-design on a 40nm 256K resistive memory macro, observing 17.3% and 19.9% accuracy improvements in image and audio classification on FashionMNIST and Spoken digits datasets, as well as 9.8% (2%) improvement in PR (ROC) in image segmentation on DRIVE datasets, r

关键词： Energy utilization

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：