检索结果-内蒙古大学图书馆

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Do, Tien H. Nguyen, Huy Q. Le, Hoang D. Pham, Hien T. T. Nguyen, Thang V. Dang, Ngoc T. Posts and Telecommunications Institute of Technology Wireless Systems and Applications Lab. Hanoi Viet Nam The University of Aizu Computer Communications Laboratory Aizuwakamatsu965-8580 Japan

ISBN: (纸本)9798350353983

Air-ground integrated network (AGIN) incorporating high-altitude platforms (HAP), unmanned aerial vehicles (UAV), and ground base stations (BS) has been recently rec-ognized as a promising architecture for 6G wireless networks. In addition, free-space optical (FSO) technology has shown its potential for delivering exceptionally high-speed data connections over a long distance. While previous works on FSO-based AGIN mainly focused on point-to-point connectivity, this study instead addresses the context of multiple users. This, in turn, raises concerns about the effective multiple access control (MAC) protocol design. In this study, we analyze the performance of MAC protocols, which jointly employ the rate adaptation and bandwidth allocation, in FSO-based AGIN. Particularly, we exploit the performance of different rate adaptation/bandwidth allocation-based MAC protocols for UAV-aided relaying between multiple BSs and HAP via FSO links. Performance metrics are analytically obtained based on Markov models, including frame loss probability, system throughput and average delay. Numerical results offer insights for properly choosing MAC protocols for FSO-based AGIN towards 6G wireless networks. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning 41

Towards Efficient Deep Spiking Neural Networks Construction ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Yaxin Xu, Qi Shen, Jiangrong Xu, Hongming Chen, Long Pan, Gang School of Computer Science and Technology Dalian University of Technology Dalian China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China College of Computer Science and Technology Zhejiang University Hangzhou China Centre for Systems Engineering and Innovation Imperial College London London United Kingdom

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant structural units, aiming to more effectively leverage their low-power consumption and biological interpretability advantages. Currently, most model compression techniques for SNNs are based on unstructured pruning of individual connections, which requires specific hardware support. Hence, we propose a structured pruning approach based on the activity levels of convolutional kernels named Spiking Channel Activity-based (SCA) network pruning framework. Inspired by synaptic plasticity mechanisms, our method dynamically adjusts the network's structure by pruning and regenerating convolutional kernels during training, enhancing the model's adaptation to the current target task. While maintaining model performance, this approach refines the network architecture, ultimately reducing computational load and accelerating the inference process. This indicates that structured dynamic sparse learning methods can better facilitate the application of deep SNNs in low-power and high-efficiency scenarios. Copyright 2024 by the author(s)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

HyFiSS: A Hybrid Fidelity Stall-Aware Simulator for GPGPUs 57

HyFiSS: A Hybrid Fidelity Stall-Aware Simulator for GPGPUs

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Yang, Jianchao Wen, Mei Chen, Dong Chen, Zhaoyun Xue, Zeyu Li, Yuhang Shen, Junzhong Shi, Yang College of Computer National University of Defense Technology Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China Huawei Technologies Co. Ltd Beijing China

ISBN: (纸本)9798350350579

The widespread adoption of GPUs has driven the development of GPU simulators, which, in turn, lead advancements in both GPU architectures and software optimization. Trace-driven cycle-Accurate Cycle-Accurate simulators, which provide detailed microarchitectural models and clock-level precision, come at the cost of extended simulation times and require high computational resources. Their scalability has become a bottleneck. A growing trend is the adoption of cycle-Approximate simulators, which introduce mathematical modeling of partial hardware units and utilize sampling to accelerate simulation. However, this approach faces challenges regarding the accuracy of performance predictions. To address these limitations, we introduce HyFiSS, a hybrid fidelity stall-Aware GPU simulator. HyFiSS features fine-grained stall events tracking and attribution by constructing a detailed execution pipeline model for various stall events on Streaming Multiprocessors (SMs). It accurately emulates the thread block scheduler behavior using real-Time scheduling logs and utilizes sampling based on thread block sets to minimize the precision loss due to fine-grained sampling points on the microarchitectural state. We achieve a balance between reliability, speed, and the level of simulation detail, especially regarding bottlenecks. By evaluating a diverse set of benchmarks, HyFiSS achieves a mean absolute percentage error in predicting active cycles that is comparable to the state-of-The-Art cycle-Accurate simulator Accel-Sim. Moreover, HyFiSS achieves a substantial 12.8 × speedup in the simulation efficiency compared to Accel-Sim. HyFiSS also requires at least 3.2 × less disk storage than both Accel-Sim and another state-of-The-Art cycle-Approximate simulator PPT-GPU due to its efficient SASS (Streaming Assembler) traces compression. With precise, per-cycle stall events statistics, HyFiSS can provide accurate GPU performance metrics and stall cause reporting. This significantly simplifies

关键词： GPGPU Simulation Workload Characterization

来源：评论

学校读者我要写书评

暂无评论

Positive and Unlabeled Learning with Controlled Probability Boundary Fence 41

Positive and Unlabeled Learning with Controlled Probability ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Changchun Dai, Yuanchao Feng, Lei Li, Ximing Wang, Bing Ouyang, Jihong College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

Positive and Unlabeled (PU) learning refers to a special case of binary classification, and technically, it aims to induce a binary classifier from a few labeled positive training instances and loads of unlabeled instances. In this paper, we derive a theorem indicating that the probability boundary of the asymmetric disambiguation-free expected risk of PU learning is controlled by its asymmetric penalty, and we further empirically evaluated this theorem. Inspired by the theorem and its empirical evaluations, we propose an easy-to-implement two-stage PU learning method, namely Positive and Unlabeled Learning with Controlled Probability Boundary Fence (PUL-CPBF). In the first stage, we train a set of weak binary classifiers concerning different probability boundaries by minimizing the asymmetric disambiguation-free empirical risks with specific asymmetric penalty values. We can interpret these induced weak binary classifiers as a probability boundary fence. For each unlabeled instance, we can use the predictions to locate its class posterior probability and generate a stochastic label. In the second stage, we train a strong binary classifier over labeled positive training instances and all unlabeled instances with stochastic labels in a self-training manner. Extensive empirical results demonstrate that PUL-CPBF can achieve competitive performance compared with the existing PU learning baselines. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Counterfactual discriminative micro-expression recognition

引用

Visual Intelligence 2024年第1期2卷 1-10页

作者： Li, Yong Liu, Menglin Lao, Lingjie Wang, Yuanzhi Cui, Zhen Department of Computer Science City University of Hong Kong 999077 Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

Micro-expressions are spontaneous, rapid and subtle facial movements that can hardly be suppressed or fabricated. Micro-expression recognition (MER) is one of the most challenging topics in affective computing. It aims to recognize subtle facial movements which are quite difficult for humans to perceive in a fleeting period. Recently, many deep learning-based MER methods have been developed. However, how to effectively capture subtle temporal variations for robust MER still perplexes us. We propose a counterfactual discriminative micro-expression recognition (CoDER) method to effectively learn the slight temporal variations for video-based MER. To explicitly capture the causality from temporal dynamics hidden in the micro-expression (ME) sequence, we propose ME counterfactual reasoning by comparing the effects of the facts w.r.t. original ME sequences and the counterfactuals w.r.t. counterfactually-revised ME sequences, and then perform causality-aware prediction to encourage the model to learn those latent ME temporal cues. Extensive experiments on four widely-used ME databases demonstrate the effectiveness of CoDER, which results in comparable and superior MER performance compared with that of the state-of-the-art methods. The visualization results show that CoDER successfully perceives the meaningful temporal variations in sequential faces. © The Author(s) 2024.

关键词： Affective computing Causal graph Counterfactual reasoning Micro-expression recognition Temporal variation

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Classification Using Deep and Quantum Neural Networks

Traffic Sign Classification Using Deep and Quantum Neural Ne...

引用

International Conference on computer Vision and Graphics, ICCVG 2022

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Light field depth estimation:A comprehensive survey from principles to future

引用

High-Confidence Computing 2024年第1期4卷 92-107页

作者： Tun Wang Hao Sheng Rongshan Chen Da Yang Zhenglong Cui Sizhe Wang Ruixuan Cong Mingyuan Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Zhongfa Aviation Institute Beihang UniversityHangzhou 311115China Faculty of Applied Sciences Macao Polytechnic UniversityMacao 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Light Field(LF)depth estimation is an important research direction in the area of computer vision and computational photography,which aims to infer the depth information of different objects in threedimensional scenes by capturing LF *** this new era of significance,this article introduces a survey of the key concepts,methods,novel applications,and future trends in this *** summarize the LF depth estimation methods,which are usually based on the interaction of radiance from rays in all directions of the LF data,such as epipolar-plane,multi-view geometry,focal stack,and deep *** analyze the many challenges facing each of these approaches,including complex algorithms,large amounts of computation,and speed *** addition,this survey summarizes most of the currently available methods,conducts some comparative experiments,discusses the results,and investigates the novel directions in LF depth estimation.

关键词： Light field Depth estimation Deep learning Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

Intelligent Control Based in Neural-Fuzzy of Adaptive Backstepping for The Double Stator IPMSM Powered by a Five-Level NPC Inverter 13

Intelligent Control Based in Neural-Fuzzy of Adaptive Backst...

引用

13th IEEE International Conference and Expositions on Electric and Power Engineering, EPEi 2024

作者： Benaissa, Rabie Mansouri, Smail Ouledali, Omar University of Adrar Faculty of Sciences and Technology Department of Electrical Engineering Laboratory for Sustainable Development and Computer Science 01000 Algeria University of Adrar Faculty of Sciences and Technology Department of Hydrocarbons and Renewable Energies Laboratory for Energy Environment and Information Systems 01000 Algeria

ISBN: (纸本)9798350356199

This article supplies a proposed approach Neuro Fuzzy Controller (NFC)-Adaptive Backstepping Controller (ABC)-Space Vector Modulation (SVM) for a five-level NPC inverter-Double Stator Interior Permanent Magnet Synchronous Motor (DSIPMSM). This paper's primary objective is to enhance DSIPMSM's performance by the use of strong control using the proposed approach. Given its benefits - including high torque density, high efficiency, high power density, and minimal maintenance - DSIPMSM, have recently been the focus of much research. Using the input-output linearization approach and Lyapunov stability theory, asymptotically stable trajectory-following dynamics are demonstrated using nonlinear adaptive backstepping control. The use of fuzzy logic and intelligence-based controllers are increasingly being used to enhance traditional control's performance and output. In addition, the fuzzy logic controller has a lot of flaws that are presently being fixed by the extremely effective NFC tool. The proposed method's worth was demonstrated by the simulation results in terms of durability, effective tracking dynamics, precision, and good disturbance rejection with little ripple. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on computer Vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

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：