检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yu, Yifei Wang, Shaocong Zhang, Woyu Zhang, Xinyuan Wu, Xiuzhe He, Yangu Yang, Jichang Zhang, Yue Lin, Ning Wang, Bo Chen, Xi Wang, Songqi Zhang, Xumeng Qi, Xiaojuan Wang, Zhongrui Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Hong Kong Institute of Mind The University of Hong Kong Hong Kong Hong Kong Key Lab of Fabrication Technologies for Integrated Circuits Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China University of Chinese Academy of Sciences Beijing100049 China 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 Hong Kong

Human beings construct perception of space by integrating sparse observations into massively interconnected synapses and neurons, offering a superior parallelism and efficiency. Replicating this capability in AI finds wide applications in medical imaging, AR/VR, and embodied AI, where input data is often sparse and computing resources are limited. However, traditional signal reconstruction methods on digital computers face both software and hardware challenges. On the software front, difficulties arise from storage inefficiencies in conventional explicit signal representation. Hardware obstacles include the von Neumann bottleneck, which limits data transfer between the CPU and memory, and the limitations of CMOS circuits in supporting parallel processing. We propose a systematic approach with software-hardware co-optimizations for signal reconstruction from sparse inputs. Software-wise, we employ neural field to implicitly represent signals via neural networks, which is further compressed using low-rank decomposition and structured pruning. Hardware-wise, we design a resistive memory-based computing-in-memory (CIM) platform, featuring a Gaussian Encoder (GE) and an MLP Processing Engine (PE). The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit. We demonstrate the system’s efficacy on a 40nm 256Kb resistive memory-based in-memory computing macro, achieving 31.5×, 35.5×, and 47.2× energy efficiency improvements and 10.8×, 38.8×, and 6.2× parallelism improvements without compromising reconstruction quality in tasks like 3D CT sparse reconstruction, novel view synthesis, and novel view synthesis for dynamic scenes. This work advances the AI-driven signal restoration technology and paves the way for future efficient and robust medical AI and 3D vision applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal reconstruction

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

Towards Effective Resource Procurement in MEC: a Resource Re-selling Framework

arXiv

引用

arXiv 2022年

作者： Siew, Marie Sharma, Shikhar Guo, Kun Cai, Desmond Wen, Wanli Joe-Wong, Carlee Quek, Tony Q.S. The Electrical and Computer Engineering Department Carnegie Mellon University PittsburghPA15213 United States The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The School of Communications and Electronics Engineering East China Normal University Shanghai200241 China The School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China The Singapore University of Technology and Design 487372 Singapore The Yonsei Frontier Lab Yonsei University Korea Republic of

On-demand and resource reservation pricing models, widely used in cloud computing, are currently used in Multi-Access Edge Computing (MEC). Nevertheless the edge’s resources are distributed and each server has lower capacity. If too much resources were reserved in advance, on-demand users may not get their jobs served on time, jeopardizing MEC’s latency benefits. Concurrently, reservation plan users may possess un-used quota. Therefore, we propose a sharing platform where reservation plan users can re-sell unused resource quota to on-demand users. To investigate the mobile network operator’s (MNO’s) incentive of allowing re-selling, we formulate a 3-stage non-cooperative Stackelberg Game and characterize the optimal strategies of buyers and re-sellers. We show that users’ actions give rise to 4 different outcomes at equilibrium, dependent on the prices and supply levels of the sharing and on-demand pools. Based on the 4 possible outcomes, we characterise the MNO’s optimal prices for on-demand users. Numerical results show that having both pools gives the MNO an optimal revenue when the on-demand pool’s supply is low, and unexpectedly, when the MNO’s commission is low. We develop an interactive prototype, and show that users’ decision distributions in studies on our prototype are similar to that of our decision model. © 2022, CC BY.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Dynamic neural network with memristive CIM and CAM for 2D and 3D vision

arXiv

引用

arXiv 2024年

作者： Zhang, Yue Zhang, Woyu Wang, Shaocong Lin, Ning Yu, Yifei He, Yangu Wang, Bo Jiang, Hao Lin, Peng Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Zhang, Xumeng 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 Beijing100049 China 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 Lab of Fabrication Technologies for Integrated Circuits Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China University of Chinese Academy of Sciences Beijing100049 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

The brain is dynamic, associative and efficient. It reconfigures by associating the inputs with past experiences, with fused memory and processing. In contrast, AI models are static, unable to associate inputs with past experiences, and run on digital computers with physically separated memory and processing. We propose a hardware-software co-design, a semantic memory-based dynamic neural network (DNN) using memristor. The network associates incoming data with the past experience stored as semantic vectors. The network and the semantic memory are physically implemented on noise-robust ternary memristor-based Computing-In-Memory (CIM) and Content-Addressable Memory (CAM) circuits, respectively. We validate our co-designs, using a 40nm memristor macro, on ResNet and PointNet++ for classifying images and 3D points from the MNIST and ModelNet datasets, which not only achieves accuracy on par with software but also a 48.1% and 15.9% reduction in computational budget. Moreover, it delivers a 77.6% and 93.3% reduction in energy consumption. © 2024, CC BY.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Resistive memory-based zero-shot liquid state machine for multimodal event data learning

arXiv

引用

arXiv 2023年

作者： Lin, Ning Wang, Shaocong Li, Yi Wang, Bo Shi, Shuhui He, Yangu Zhang, Woyu Yu, Yifei Zhang, Yue Zhang, Xinyuan Wong, Kwunhang Wang, Songqi Chen, Xiaoming Jiang, Hao Zhang, Xumeng Lin, Peng Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Shang, Dashan Liu, Qi Liu, Ming Department of Electrical and Electronic Engineering the University of Hong Kong Hong Kong Key Lab of Fabrication Technologies for Integrated Circuits and Key Laoratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics the Chinese Academy of Sciences Beijing100029 China The School of Microelectronics Southern University of Science and Technology Shenzhen518055 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 Hangzhou310027 China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

The human brain is a complex spiking neural network (SNN), capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal propagation. However, replicating the human brain in neuromorphic hardware presents both hardware and software challenges. Hardware limitations, such as the slowdown of Moore’s law and Von Neumann bottleneck, hinder the efficiency of digital computers. Additionally, SNNs are characterized by their software training complexities. To this end, we propose a hardware-software co-design on a 40 nm 256 Kb in-memory computing macro that physically integrates a fixed and random liquid state machine (LSM) SNN encoder with trainable artificial neural network (ANN) projections. We showcase the zero-shot LSM-based learning of multimodal events on the N-MNIST and N-TIDIGITS datasets, including visual and audio data association, as well as neural and visual data alignment for brain-machine interfaces. Our co-design achieves classification accuracy comparable to fully optimized software models, resulting in a 152.83 and 393.07-fold reduction in training costs compared to SOTA contrastive language-image pre-training (CLIP) and Prototypical networks, and a 23.34 and 160-fold improvement in energy efficiency compared to cutting-edge digital hardware, respectively. These proof-of-principle prototypes demonstrate zero-shot multimodal events learning capability for emerging efficient and compact neuromorphic hardware. © 2023, CC BY-NC-SA.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Observation of intrinsic chiral bound states in the continuum

arXiv

引用

arXiv 2022年

作者： Chen, Yang Deng, Huachun Sha, Xinbo Chen, Weijin Wang, Ruize Chen, Yuhang Wu, Dong Chu, Jiaru Kivshar, Yuri S. Xiao, Shumin Qiu, Cheng-Wei Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Chinese Academy of Sciences Key Laboratory of Mechanical Behavior and Design of Materials Department of Precision Machinery and Precision Instrumentation University of Science and Technology of China Hefei230027 China Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Harbin Institute of Technology Shenzhen518055 China Nonlinear Physics Center Research School of Physics Australian National University CanberraACT2601 Australia Pengcheng Laboratory Shenzhen518055 China

Photons with spin angular momentum possess intrinsic chirality which underpins many phenomena including nonlinear optics1, quantum optics2, topological photonics3 and chiroptics4. Intrinsic chirality is weak in natural materials, and recent theoretical proposals5-7 aimed to enlarge circular dichroism by resonant metasurfaces supporting bound states in the continuum that enhance substantially chiral light-matter interaction. Those insightful works resort to three-dimensional sophisticated geometries, which are too challenging to be realized for optical frequencies8. Therefore, most of the experimental attempts9-11 showing strong circular dichroism rely on false/extrinsic chirality by employing either oblique incidence9, 10 or structural anisotropy11. Here, we report on the experimental realization of true/intrinsic chiral response with resonant metasurfaces where the engineered slant geometry breaks both in-plane and out-of-plane symmetries. Our result marks the first observation of intrinsic chiral bound states in the continuum with near-unity chiral dichroism of 0.93 and record-high quality factor exceeding 2663 for visible frequencies. Our chiral metasurfaces promise a plethora of applications in chiral light sources and detectors, chiral sensing, valleytronics and asymmetric photocatalysis. © 2022, CC BY.

关键词： Dichroism

来源：评论

学校读者我要写书评

暂无评论

A Write-Improved Half-Select-Free Low-Power 11T Subthreshold SRAM with Double Adjacent Error Correction for FPGA-LUT design 22nd

A Write-Improved Half-Select-Free Low-Power 11T Subthreshold...

引用

22nd International Symposium on VLSI design and Test, VDAT 2018

作者： Sharma, Vishal Bisht, Pranshu Dalal, Abhishek Chouhan, Shailesh Singh Jattana, H.S. Vishvakarma, Santosh Kumar Nanoscale Devices VLSI Circuit and System Design Lab Electrical Engineering Indian Institute of Technology Indore IndoreM.P.453552 India EISLAB Department of Computer Science Electrical and Space Engineering Lulea University of Technology Lulea Sweden SCL Mohali Department of Space Govt. of India AjitgarhPunjab India

ISBN: (纸本)9789811359491

This work presents a new bit-interleaving low-power 11T subthreshold SRAM cell with the Data-Dependent Partial-Feedback Cutting to improve the write ability. The isolated read path of 11T enhances the read static noise margin (RSNM) which is equivalent to that of its hold SNM (HSNM), while the incorporated PMOS stacking in each of the inverter helps to reduce the leakage power of the cell. The half-select free behavior of the proposed 11T cell facilitates the bit-interleaving architecture of memory array that reduces the multi-bits error occurrence in a single word of data, and thus enhance the soft error tolerance. Using the proposed cell, a four-input FPGA lookup table (LUT) has been implemented working on 0.4V supply, which consumes 0.59 less leakage power as compared to that of 6T LUT. Finally, a two adjacent bits error correction technique is also suggested to incorporate with the proposed bit-interleaving 11T array, so that the effect of soft error can almost be neglected. It consumes comparable leakage and read access energy to that of one-bit error correcting conventional hamming code. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Generalized Scaling Law for Exciton Binding Energy in Two-Dimensional Materials

引用

Physical Review Applied 2020年第6期13卷 064062-064062页

作者： S. Ahmad M. Zubair O. Jalil M. Q. Mehmood U. Younis X. Liu K. W. Ang L. K. Ang Electrical Engineering Department Information Technology University (ITU) of the Punjab Lahore 54000 Pakistan NanoTech Lab Electrical Engineering Department Information Technology University (ITU) of the Punjab Lahore 54000 Pakistan College of Materials Science and Engineering Shenzhen Key Laboratory of Microscale Optical Information Technology Chinese Engineering and Research Institute of Microelectronics Shenzhen University 3688 Nanhai Avenue Shenzhen 518060 People’s Republic of China Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore Science and Math Cluster Singapore University of Technology and Design (SUTD) 8 Somapah Road Singapore 487372 Singapore

Binding energy calculation in two-dimensional (2D) materials is crucial in determining their electronic and optical properties pertaining to enhanced Coulomb interactions between charge carriers due to quantum confinement and reduced dielectric screening. Based on full solutions of the Schrödinger equation in a screened hydrogen model with a modified Coulomb potential (1/rβ−2), we present a generalized and analytical scaling law for the exciton binding energy, Eβ=E0(aβb+c)(μ/ϵ2), where β is a fractional-dimension parameter that accounts for the reduced dielectric screening. The model is able to provide accurate binding energies, benchmarked using the reported Bethe-Salpeter equation and experimental data, for 58 monolayer 2D and eight bulk materials, respectively, through β. For a given material, β is varied from β=3 for bulk three-dimensional materials to a value lying in the range 2.55–2.7 for 2D monolayer materials. With βmean=2.625, our model improves the average relative mean square error by a factor of 3 in comparison to existing models. The results can be used for Coulomb engineering of exciton binding energies in the optimal design of 2D materials.

关键词： Excitons Optoelectronics 2-dimensional systems Quantum wells Semiconductors Scaling methods

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Large circuit models: opportunities and challenges

引用

SCIENCE CHINA Information Sciences 2024年第11期67卷 1-1页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y. YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah's Ark Lab Hong Kong 999077 China School of Integrated Circuits Peking University Beijing 100871 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo 315211 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong 999077 China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong 999077 China School of Integrated Circuits Southeast University Nanjing 210096 China Huawei HiSilicon Shenzhen 518129 China Peng Cheng Laboratory Shenzhen 518052 China School of Computer Science Peking University Beijing 100871 China School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University Shanghai 200433 China School of Artificial Intelligence Shanghai Jiao Tong University Shanghai 200240 China

来源：评论

学校读者我要写书评

暂无评论

Intelligent spectrum learning for wireless networks with reconfigurable intelligent surfaces

arXiv

引用

arXiv 2021年

作者： Yang, Bo Cao, Xuelin Huang, Chongwen Yuen, Chau Qian, Lijun Renzo, Marco Di Engineering Product Development Pillar Singapore University of Technology and Design Singapore487372 Singapore Zhejiang Provincial Key Lab of information processing communication and networking Zhejiang University No.38 Zheda Road Hangzhou310007 China Department of Electrical and Computer Engineering CREDIT Center Prairie View A&M University Texas A&M University System Prairie ViewTX77446 United States Université Paris-Saclay CNRS CentraleSupélec Laboratoire des Signaux et Systèmes 3 Rue Joliot-Curie Gif-sur-Yvette91192 France

Reconfigurable intelligent surface (RIS) has become a promising technology for enhancing the reliability of wireless communications, which is capable of reflecting the desired signals through appropriate phase shifts. However, the intended signals that impinge upon an RIS are often mixed with interfering signals, which are usually dynamic and unknown. In particular, the received signal-to-interference-plus-noise ratio (SINR) may be degraded by the signals reflected from the RISs that originate from non-intended users. To tackle this issue, we introduce the concept of intelligent spectrum learning (ISL), which uses an appropriately trained convolutional neural network (CNN) at the RIS controller to help the RISs infer the interfering signals directly from the incident signals. By capitalizing on the ISL, a distributed control algorithm is proposed to maximize the received SINR by dynamically configuring the active/inactive binary status of the RIS elements. Simulation results validate the performance improvement offered by deep learning and demonstrate the superiority of the proposed ISL-aided approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：