检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Kozal, Jedrzej Wozniak, Michal Department of Systems and Computer Networks Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wybrzeze Wyspianskiego 27 Wroclaw50-370 Poland

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a novel approach based on adding new layers on top of existing ones to enable the forward transfer of knowledge and adapting previously learned representations. We employ a method of determining the most similar tasks for selecting the best location in our network to add new nodes with trainable parameters. This approach allows for creating a treelike model, where each node is a set of neural network parameters dedicated to a specific task. The Progressive Neural Network concept inspires the proposed method. Therefore, it benefits from dynamic changes in network structure. However, Progressive Neural Network allocates a lot of memory for the whole network structure during the learning process. The proposed method alleviates this by adding only part of a network for a new task and utilizing a subset of previously trained weights. At the same time, we may retain the benefit of PNN, such as no forgetting guaranteed by design, without needing a memory buffer. Results: Experiments on Split CIFAR and Split Tiny ImageNet show that the proposed algorithm is on par with other continual learning methods. In a more challenging setup with a single computer vision dataset as a separate task, our method outperforms Experience Replay. Conclusion: It is compatible with commonly used computer vision architectures and does not require a custom network structure. As an adaptation to changing data distribution is made by expanding the architecture, there is no need to utilize a rehearsal buffer. For this reason, our method could be used for sensitive applications where data privacy must be considered. © 2022, CC BY.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Optical coherent dot-product chip for sophisticated deep learning regression

引用

Light(science & Applications) 2021年第12期10卷 2330-2341页

作者： Shaofu Xu Jing Wang Haowen Shu Zhike Zhang Sicheng Yi Bowen Bai Xingjun Wang Jianguo Liu Weiwen Zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong University800 Dongchuan RoadShanghai 200240China State Key Laboratory of Advanced Optical Communications System and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China Institution of Semiconductors Chinese Academy of SciencesBeijing 100083China

Optical implementations of neural networks(ONNs)herald the next-generation high-speed and energy-efficient deep learning computing by harnessing the technical advantages of large bandwidth and high parallelism of ***,due to the problems of the incomplete numerical domain,limited hardware scale,or inadequate numerical accuracy,the majority of existing ONNs were studied for basic classification *** that regression is a fundamental form of deep learning and accounts for a large part of current artificial intelligence applications,it is necessary to master deep learning regression for further development and deployment of ***,we demonstrate a silicon-based optical coherent dot-product chip(OCDC)capable of completing deep learning regression *** OCDC adopts optical fields to carry out operations in the complete real-value domain instead of in only the positive *** reusing,a single chip conducts matrix multiplications and convolutions in neural networks of any ***,hardware deviations are compensated via in-situ backpropagation control provided the simplicity of chip ***,the OCDC meets the requirements for sophisticated regression tasks and we successfully demonstrate a representative neural network,the AUTOMAP(a cutting-edge neural network model for image reconstruction).The quality of reconstructed images by the OCDC and a 32-bit digital computer is *** the best of our knowledge,there is no precedent of performing such state-of-the-art regression tasks on ONN *** is anticipated that the OCDC can promote the novel accomplishment of ONNs in modern AI applications including autonomous driving,natural language processing,and scientific study.

关键词： neural hardware coherent

来源：评论

学校读者我要写书评

暂无评论

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polarization Configuration for Geophysical Rotation Sensing

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polariz...

引用

2021 Asia communications and Photonics Conference, ACP 2021

作者： Chen, Yanjun Cao, Yuwen Wang, Wenbo He, Yan Zhou, Tong Li, Zhengbin State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China School of Software and Microelectronics Peking University Beijing102600 China

A fiber optic gyroscope based on dual-polarization configuration_is designed and realized. The 24-hour stability test shows aself-noise level of 3 × 10−9 rad/s/√Hz within the frequency range of 0.001Hz to 1Hz. &... 详细信息

ISBN: (纸本)9781957171005

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Flexible Measurement Testbed for Evaluating Time-Sensitive Networking in Industrial Automation Applications

Flexible Measurement Testbed for Evaluating Time-Sensitive N...

引用

IEEE Conference on Network Softwarization (NetSoft)

作者： Stefan Senk Marian Ulbricht Javier Acevedo Giang T. Nguyen Patrick Seeling Frank H. P. Fitzek Deutsche Telekom Chair of Communication Networks TU Dresden Haptic Communication Systems TU Dresden Centre for Tactile Internet with Human-in-the-Loop (CeTI) Department of Computer Science Central Michigan University

ISBN: (数字)9781665406949

ISBN: (纸本)9781665406956

Deterministic communications are required for industrial environments, yet their realization is a challenging task. Time-Sensitive Networking (TSN) is intended to enable deterministic communication over inexpensive Ethernet networks. Standardized by the IEEE TSN working group, TSN enables precise control of time synchronization, traffic shaping, reliability enhancements, and network administration to answer the demands of industrial control applications. Subsequently, there is a significant need to enable turnkey research and implementation efforts. However, a current lack of open-sourced testbed implementations to investigate and study the behavior of TSN network devices limits verification to simulation and theoretical models. We introduce a publicly available, flexible, and open-sourced measurement testbed for evaluating TSN in the context of industrial automation applications to address the need to perform real-world measurements. In this contribution, we describe our testbed combining Commercial-Off-The-Shelf (COTS) hardware and existing open-source tools as a platform for in-depth evaluation of TSN devices. Providing detailed TSN backgrounds, we describe an in-depth performance analysis for our implementation. For a common Tactile Internet scenario, we observe an accuracy of close to 5 ns achievable with our publicly available COTS setup.

关键词： Performance evaluation Automation Turnkey project Current measurement Hardware Behavioral sciences Software measurement

来源：评论

学校读者我要写书评

暂无评论

LLM4WM: Adapting LLM for Wireless Multi-Tasking

arXiv

引用

arXiv 2025年

作者： Liu, Xuanyu Gao, Shijian Liu, Boxun Cheng, Xiang Yang, Liuqing State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China Guangzhou511400 China Guangzhou511400 China Department of Electronic and Computer Engineering The Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong

The wireless channel is fundamental to communication, encompassing numerous tasks collectively referred to as channel-associated tasks. These tasks can leverage joint learning based on channel characteristics to share representations and enhance system design. To capitalize on this advantage, LLM4WM is proposed—a large language model (LLM) multi-task fine-tuning framework specifically tailored for channel-associated tasks. This framework utilizes a Mixture of Experts with Low-Rank Adaptation (MoE-LoRA) approach for multi-task fine-tuning, enabling the transfer of the pre-trained LLM’s general knowledge to these tasks. Given the unique characteristics of wireless channel data, preprocessing modules, adapter modules, and multi-task output layers are designed to align the channel data with the LLM’s semantic feature space. Experiments on a channel-associated multi-task dataset demonstrate that LLM4WM outperforms existing methodologies in both full-sample and few-shot evaluations, owing to its robust multi-task joint modeling and transfer learning capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator

PAM-4 optical transmission beyond 224 Gbps based on an ultra...

引用

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

We experimentally demonstrate PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator in C-band with the combination of the artificial neural network equalizers. © ... 详细信息

关键词： Light modulators

来源：评论

学校读者我要写书评

暂无评论

PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator

PAM-4 optical transmission beyond 224 Gbps based on an ultra...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-Optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

ISBN: (纸本)9781957171395

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Radar Probing Optimization for Joint Beamforming and UAV Trajectory Design in UAV-Enabled Integrated Sensing and communication

引用

IEEE Transactions on communications 2024年

作者： Liu, Yaxi Mao, Wencan He, Boxin Huangfu, Wei Huang, Tianyao Zhang, Haijun Long, Keping University Of Science And Technology Beijing Beijing Advanced Innovation Center For Materials Genome Engineering Beijing Engineering And Technology Research Center For Convergence Networks And Ubiquitous Services School Of Computer And Communication Engineering Beijing100083 China University Of Science And Technology Shunde Innovation School Beijing China National Institute Of Informatics Information Systems Architecture Science Research Division Tokyo101-8430 Japan

Unmanned aerial vehicle (UAV)-enabled massive multiple-input-multiple-output (MIMO) integrated sensing and communication (ISAC) is an emerging platform to perform communication and sensing efficiently and flexibly. However, the existing works barely consider the radar probing tasks and neglect the benefits of the dedicated sensing signal. In this paper, we focus on joint optimizations in radar probing tasks, and a novel indicator is introduced, namely radar probing error. Two optimizations in radar probing tasks are established: i) joint transmit beamforming design for large-scale regional radar probing and communication task;ii) joint transmit beamforming and UAV trajectory design for communication enhancement and radar probing task. For the former task, we adopt both communication and novel sensing precoders to further support the MIMO radar. A semidefinite relaxation is utilized to relax the original non-convex problem, which is proven to be tight. For the latter task, we adopt block coordinate descent to alternately optimize the precoders and UAV trajectory where the fractional programming approach and successive convex approximation are further adopted. Experiment results testify the validation of the proposed methods for radar probing tasks in UAV-enabled MIMO ISAC. Moreover, results show the fundamental trade-off between the dual functions and reveal the effectiveness of the introduced sensing precoder. © 1972-2012 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

Active Weighted Aging Ensemble for Drifted Data Stream

SSRN

引用

SSRN 2022年

作者： Woźniak, Michal Zyblewski, Pawel Ksieniewicz, Pawel Department of Systems and Computer Networks Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wybrzeźe Wyspiańskiego 27 Wroclaw50-370 Poland

One of the significant problems in streaming data classification is the concept drift phenomenon, which consists of the change in probabilistic characteristics of the classification task. Such changes in posterior probability destabilize the classification model performance, seriously degrading its quality. It is necessary to design appropriate strategies to counteract this phenomenon, allowing the classifier to adapt to the changing probabilistic characteristics. Especially difficult is to propose such an approach with the limited access to data labels. A human bias of high quality is usually costly, so to minimize the expenses related to this process, it is also necessary to propose learning strategies based on semi-supervised learning. Such strategies employ active learning methods indicating which of the incoming objects are valuable to be labeled for improving the classifier’s performance. This paper proposes a novel chunk-based method for non-stationary data streams based on ensemble and active learning paradigms, considering a limited budget that may be applied to any data stream classification algorithm. The proposed method has been evaluated through computer experiments using real and synthetic data streams, which confirm the high quality of the proposed algorithm over state-of-the-art methods. © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

problexity — an open-source Python library for binary classification problem complexity assessment

arXiv

引用

arXiv 2022年

作者： Komorniczak, Joanna Ksieniewicz, Pawel Department of Systems and Computer Networks Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wybrzeże Wyspiańskiego 27 Wroclaw50-370 Poland

The classification problem’s complexity assessment is an essential element of many topics in the supervised learning domain. It plays a significant role in meta-learning – becoming the basis for determining meta-attributes or multicriteria optimization – allowing the evaluation of the training set resampling without needing to rebuild the recognition model. The tools currently available for the academic community, which would enable the calculation of problem complexity measures, are available only as libraries of the C++ and R languages. This paper describes the software module that allows for the estimation of 22 complexity measures for the Python language – compatible with the scikit-learn programming interface – allowing for the implementation of research using them in the most popular programming environment of the machine learning community. © 2022, CC BY.

关键词： Python

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：