检索结果-内蒙古大学图书馆

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Dhawal Gupta Gabor Mihucz Matthew K. Schlegel James E. Kostas Philip S. Thomas Martha White Department of Computing Science Alberta Machine Intelligence Institute (Amii) University of Alberta College of Information and Computer Sciences University of Massachusetts Department of Computing Science CIFAR AI Chair Amii University of Alberta

ISBN: (纸本)9781713845393

Structural credit assignment in neural networks is a long-standing problem, with a variety of alternatives to backpropagation proposed to allow for local training of nodes. One of the early strategies was to treat each node as an agent and use a reinforcement learning method called REINFORCE to update each node locally with only a global reward signal. In this work, we revisit this approach and investigate if we can leverage other reinforcement learning approaches to improve learning. We first formalize training a neural network as a finite-horizon reinforcement learning problem and discuss how this facilitates using ideas from reinforcement learning like off-policy learning. We show that the standard on-policy REINFORCE approach, even with a variety of variance reduction approaches, learns suboptimal solutions. We introduce an off-policy approach, to facilitate reasoning about the greedy action for other agents and help overcome stochasticity in other agents. We conclude by showing that these networks of agents can be more robust to correlated samples when learning online.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliable Multihop Routing and Congestion Aware Chicken Swarm Optimization in Vehicular Ad-Hoc Network

Reliable Multihop Routing and Congestion Aware Chicken Swarm...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Cuddapah Anitha Dalia Al-Tarazi GD. Vignesh A. Vinotha Vasuki Jayant Giri M. Dinesh Department of Computer Science and Engineering School of Computing Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Tirupati India Department of Architecture Engineering Faculty of Engineering Zarqa university Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia Department of Electronics and Communication Engineering St. Joseph's College of Engineering Chennai India Department of Computer Science and Engineering J.P. College of Engineering Tenkasi India Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Division of Research and Development Lovely Professional University Phagwara India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Background: Vehicular Ad Hoc Networks (VANETs) play a crucial role in intelligent transportation by facilitating communication between vehicles and vehicles with infrastructure-based models. They encounter problems such as significant movement, overcrowding, and loss of data. This research presents a novel deep reinforcement learning-based resource allocation and congestion optimization (DRLRCO) framework aimed at improving communication efficiency and high reliability using an effective learning process. Method Used: The DRLRCO framework employs agent-based learning to ensure precise data transmission, AdMAC Protocol for dynamic packet delivery, and Congestion-Aware Chicken Swarm Optimization (CSO) to enhance network performance. Result: The DRLRCO framework surpasses reinforcement learning models for comprehensive testing. Significant enhancements involve improved accuracy, reduced data loss, minimized overhead, increased throughput, and shorter average delays for real-time communication. Conclusion: The DRLRCO framework successfully tackles congestion and data loss in vehicular communication. Future studies might involve Artificial Intelligence (AI) for traffic forecasting, experimentation among high-speed vehicles and investigating blockchain for enhanced security.

关键词： Vehicular ad hoc networks Routing Throughput Synchronization Resource management Dedicated short range communication Particle swarm optimization Artificial intelligence Vehicle dynamics Testing

来源：评论

学校读者我要写书评

暂无评论

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models

Weight Sparsity Complements Activity Sparsity in Neuromorphi...

引用

Neuromorphic Systems (ICONS), International Conference on

作者： Rishav Mukherji Mark Schöne Khaleelulla Khan Nazeer Christian Mayr David Kappel Anand Subramoney Birla Institute of Technology and Science Pilani - Goa Campus Goa India Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics TU Dresden Dresden Germany Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) TU Dresden Dresden Germany Centre for Tactile Internet (CeTI) with Human-in-the-Loop TU Dresden Dresden Germany Ruhr University Bochum Institut für Neuroinformatik Germany Dept. of Computer Science Royal Holloway University of London Egham United Kingdom

ISBN: (数字)9798350368659

ISBN: (纸本)9798350368666

Activity and parameter sparsity are two standard methods of making neural networks computationally more efficient. Event-based architectures such as spiking neural networks (SNNs) naturally exhibit activity sparsity, and many methods exist to sparsify their connectivity by pruning weights. While the effect of weight pruning on feed-forward SNNs has been previously studied for computer vision tasks, the effects of pruning for complex sequence tasks like language modeling are less well studied since SNNs have traditionally struggled to achieve meaningful performance on these tasks. Using a recently published SNN-like architecture that works well on small-scale language modeling, we study the effects of weight pruning when combined with activity sparsity. Specifically, we study the tradeoff between the multiplicative efficiency gains the combination affords and its effect on task performance for language modeling. To dissect the effects of the two sparsities, we conduct a comparative analysis between densely activated models and sparsely activated event-based models across varying degrees of connectivity sparsity. We demonstrate that sparse activity and sparse connectivity complement each other without a proportional drop in task performance for an event-based neural network trained on the Penn Treebank and WikiText-2 language modeling datasets. Our results suggest sparsely connected event-based neural networks are promising candidates for effective and efficient sequence modeling.

关键词： Analytical models computer vision Event detection Neuromorphics Computational modeling Neural networks computer architecture Spiking neural networks Computational efficiency Standards

来源：评论

学校读者我要写书评

暂无评论

Lifecycle traceability towards sustainable and circular value chains: analysis framework and state of the art in the fashion industry

引用

IFAC-PapersOnLine 2022年第10期55卷 1705-1710页

作者： Riemens Joséphine Lemieux Andrée-Anne Lamouri Samir IFM-KERING Sustainability Chair Institut Français de la Mode 34 Quai d'Austerlitz 75013 Paris Laboratory of Industrial and Human Automation control Mechanical engineering and Computer Science (LAMIH – UMR CNRS 8201) Arts et Métiers Institute of Technology 151 Boulevard de l'Hôpital 75013 Paris

Tremendous environmental and social challenges have been raising traceability as a critical priority in the fashion industry. However, this traditional quality concept inherited from the food sector is prompting major confusions when it comes to sustainability and circularity transition, hindering its implementation. Based on three interrelated dimensions ( Objectives, Scope, and Action levers ) the paper proposes a novel analysis framework to conduct a literature review on lifecycle traceability towards sustainable and circular value chains in the fashion industry. Given the early stage of the topic, the paper opens significant research avenues as well as potential support to practitioners to build-up appropriate traceability action plans.

关键词： traceability transparency sustainability lifecycle supply chain fashion apparel textile

来源：评论

学校读者我要写书评

暂无评论

Efficient Optical Control of Magnon Dynamics in van der Waals Ferromagnets

引用

Ultrafast science 2024年第6期4卷 53-60页

作者： Yu Gong Zhonghua Yang Alem Teklu Ti Xie Noah Kern Andrew F.May Michael McGuire Christian Brennan Er-Jia Guo Narayanan Kuthirummal John Cetin Qian Zhang Ming Hu Cheng Gong Department of Physics and Astronomy College of CharlestonCharlestonSC 29424USA Department of Mechanical Engineering University of South CarolinaColumbiaSC 29208USA College of Architecture and Civil Engineering Shenyang University of TechnologyShenyang 110870China Department of Electrical and Computer Engineering and Quantum Technology Center University of MarylandCollege ParkMD 20742USA Materials Science and Technology Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Beijing National Laboratory for Condensed Matter Physics and Institute of Physics Chinese Academy of SciencesBeijing 100190China

Optical control of magnons in two-dimensional(2D)materials promises new functionalities for spintronics and magnonics in atomically thin ***,we report control of magnon dynamics,using laser polarization,in a ferromagnetic van der Waals(vdW)material,*** magnon amplitude,frequency,and lifetime are controlled and monitored by time-resolved pump-probe *** show substantial(over 25%)and continuous modulation of magnon dynamics as a function of incident laser *** results suggest that the modification of the effective demagnetization field and magnetic anisotropy by the pump laser pulses with different polarizations is due to anisotropic optical *** implies that pump laser pulses modify the local spin environment,which enables the launch of magnons with tunable *** first-principles calculations confirm the anisotropic optical absorption of different crystal *** findings suggest a new route for the development of opto-spintronic or opto-magnonic devices.

关键词： magnon dynamics atomically thin devicesherewe control magnon dynamicsusing van der waals ferromagnets optical control modulation magnon dynamics ferromagnetic van der waals vdw materialfe co gete optical control magnons

来源：评论

学校读者我要写书评

暂无评论

Scalable parallel flash firmware for many-core architectures 20

Scalable parallel flash firmware for many-core architectures

引用

Proceedings of the 18th USENIX Conference on File and Storage Technologies

作者： Jie Zhang Miryeong Kwon Michael Swift Myoungsoo Jung Computer Architecture and Memory Systems Laboratory Korea Advanced Institute of Science and Technology Computer Architecture and Memory Systems Laboratory University of Wisconsin at Madison

ISBN: (纸本)9781939133120

NVMe is designed to unshackle flash from a traditional storage bus by allowing hosts to employ many threads to achieve higher bandwidth. While NVMe enables users to fully exploit all levels of parallelism offered by modern SSDs, current firmware designs are not scalable and have difficulty in handling a large number of I/O requests in parallel due to its limited computation power and many hardware *** propose DeepFlash, a novel manycore-based storage platform that can process more than a million I/O requests in a second (1MIOPS) while hiding long latencies imposed by its internal flash media. Inspired by a parallel data analysis system, we design the firmware based on many-to-many threading model that can be scaled horizontally. The proposed DeepFlash can extract the maximum performance of the underlying flash memory complex by concurrently executing multiple firmware components across many cores within the device. To show its extreme parallel scalability, we implement DeepFlash on a many-core prototype processor that employs dozens of lightweight cores, analyze new challenges from parallel I/O processing and address the challenges by applying concurrency-aware optimizations. Our comprehensive evaluation reveals that DeepFlash can serve around 4.5 GB/s, while minimizing the CPU demand on microbenchmarks and real server workloads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy Mapping of Existing Building Stock in Cambridge using Energy Performance Certificates and Thermal Infrared Imagery

arXiv

引用

arXiv 2024年

作者： He, Yinglong Pan, Jiayu Debnath, Ramit Bardhan, Ronita Cullen, Luke Jenkins, Marco Gomez Mackie, Erik Hawker, George Parry, Ian Institute of Astronomy University of Cambridge CambridgeCB3 0HA United Kingdom Department of Architecture University of Cambridge CambridgeCB2 1PX United Kingdom EPRG Cambridge Judge Business School University of Cambridge CambridgeCB2 1AG United Kingdom Cambridge Zero Department of Computer Science and Technology Department of Architecture CambridgeCB3 OFD United Kingdom Division of Humanities and Social Science California Institute of Technology Pasadena91125 United States School of Mechanical Engineering Sciences University of Surrey SurreyGU2 7XH United Kingdom

Energy performance certificate (EPC) and thermal infrared (TIR) images both play a key role in the energy performance mapping of the urban building stock. In this paper, we developed parametric building archetypes using an EPC database and conducted temperature clustering on TIR images acquired through drones and satellite datasets. We evaluated 1725 EPCs of existing building stock in Cambridge, UK to generate energy consumption profiles. Drone-based TIR images of individual buildings in two Cambridge University colleges were processed using a machine learning pipeline for thermal anomaly detection and investigated the influence of two specific factors that affect the reliability of TIR for energy management applications: ground sample distance (GSD) and angle of view (AOV). The EPC-level results suggest that the construction year of the buildings influences their energy consumption. For example, modern buildings were over 30% more energy-efficient than older ones. Parallelly, older buildings were found to show almost double the energy savings potential through retrofitting than newly constructed buildings. TIR imaging results showed that thermal anomalies can only be properly identified in images with a GSD of 1m/pixel or less. A GSD of 1-6m/pixel can detect hot areas of building surfaces. We found that a GSD > 6m/pixel cannot characterise individual buildings but does help identify urban heat island effects. Additional sensitivity analysis showed that building thermal anomaly detection is more sensitive to AOV than to GSD. Our study informs newer approaches to building energy diagnostics using thermography and supports decision-making for retrofitting at a large scale. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Advancing predictive accuracy of shallow landslide using strategic data augmentation

引用

Journal of Rock Mechanics and Geotechnical Engineering 2025年

作者： Qiu, Hongzhi Chen, Xiaoqing Feng, Peng Wang, Renchao Hu, Wang Zhang, Liping Pasuto, Alessandro School of Architecture and Civil Engineering Chengdu University Chengdu 610106 China Key Laboratory of Mountain Hazards and Earth Surface Processes Institute of Mountain Hazards and Environment Chinese Academy of Sciences Chengdu 610041 China National Research Council-Research Institute for Geo-Hydrological Protection (CNR-IRPI) Padova 35127 Italy School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 China International College and Digital Innovation Chiang Mai University Chiang Mai 50200 Thailand

Rainfall-induced shallow landslides pose one of significant geological hazards, necessitating precise monitoring and prediction for effective disaster mitigation. Most studies on landslide prediction have focused on optimizing machine learning (ML) algorithms, very limited attention has been paid to enhancing data quality for improved predictive performance. This study employs strategic data augmentation (DA) techniques to enhance the accuracy of shallow landslide prediction. Using five DA methods including singular spectrum analysis (SSA), moving averages (MA), wavelet denoising (WD), variational mode decomposition (VMD), and linear interpolation (LI), we utilize strategies such as smoothing, denoising, trend decomposition, and synthetic data generation to improve the training dataset. Four machine learning algorithms, i.e. artificial neural network (ANN), recurrent neural network (RNN), one-dimensional convolutional neural network (CNN1D), and long short-term memory (LSTM), are used to forecast landslide displacement. The case study of a landslide in southwest China shows the effectiveness of our approach in predicting landslide displacements, despite the inherent limitations of the monitoring dataset. VMD proves the most effective for smoothing and denoising, improving R², RMSE, and MAPE by 172.16%, 71.82%, and 98.9%, respectively. SSA addresses missing data, while LI is effective with limited data samples, improving metrics by 21.6%, 52.59%, and 47.87%, respectively. This study demonstrates the potential of DA techniques to mitigate the impact of data defects on landslide prediction accuracy, with implications for similar cases. © 2025 institute of Rock and Soil Mechanics, Chinese Academy of sciences

关键词： Data augmentation Deformation prediction Machine learning Neural network Shallow landslide

来源：评论

学校读者我要写书评

暂无评论

District-scale surface temperatures generated from high-resolution longitudinal thermal infrared images

arXiv

引用

arXiv 2023年

作者： Lin, Subin Ramani, Vasantha Martin, Miguel Arjunan, Pandarasamy Chong, Adrian Biljecki, Filip Ignatius, Marcel Poolla, Kameshwar Miller, Clayton Berkeley Education Alliance for Research in Singapore CREATE Tower 1 Create 6 Way 138602 Singapore Robert Bosch Centre for Cyber-physical Systems Indian Institute of Science Karnataka Bengaluru560012 India Department of the Built Environment College of Design and Engineering National University of Singapore 4 Architecture Drive 117566 Singapore Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA United States Department of Architecture College of Design and Engineering National University of Singapore 4 Architecture Drive 117566 Singapore

This paper describes a dataset collected by infrared thermography, a non-contact, non-intrusive technique to acquire data and analyze the built environment in various aspects. While most studies focus on the city and building scales, an observatory installed on a rooftop provides high temporal and spatial resolution observations with dynamic interactions on the district scale. The rooftop infrared thermography observatory with a multi-modal platform capable of assessing a wide range of dynamic processes in urban systems was deployed in Singapore. It was placed on the top of two buildings that overlook the outdoor context of the National University of Singapore campus. The platform collects remote sensing data from tropical areas on a temporal scale, allowing users to determine the temperature trend of individual features such as buildings, roads, and vegetation. The dataset includes 1,365,921 thermal images collected on average at approximately 10-second intervals from two locations during ten months. © 2023, CC BY-SA.

关键词： Observatories

来源：评论

学校读者我要写书评

暂无评论

An intricate spectrogram processing in speech enhancement using machine learning with cloud computing

An intricate spectrogram processing in speech enhancement us...

引用

International Conference on Image Information Processing

作者： Yenna Geetha Reddy G Mahendran Ameer Al-Khaykan Omar A. Alkawak S. A. Kalaiselvan A. Priya Department of Computer Science and Engineering MAlla Reddy Engineering College for Women (UGC Autonomous)Kompally Secunderabad Telangana India Department of Mechancal Engineering R.M.K Engineering Collegekavaraipettai Chennai Tamil Nadu India Department of Electronic and Communications Engineering University of Kufa Najaf Iraq Department of Air Conditioning and Refrigeration Technical Engineering Al-Mustaqbal University College Hilla Babil Iraq Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Science (SIMATS) Chennai Tamil Nadu India School of Architecture Koneru Lakshmaiah Educational Foundation Guntur Andhra Pradesh India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

The spectrogram is defined as the visual representation of the signal strength with a particular interval of time regarding frequencies in the appropriate waveform. It is demonstrated using the Fourier transform. It is illustrated in a three-dimensional plot of signal composed with amplitude versus frequency and time. They are classified as long signal sections and short signal sections with filters. It demonstrates the consecutive spectacle of the sound signal at a particular interval of time. The time-frequency representation of audio signals is obtained through spectrograms. This helps in the understanding of the speech data. Machine learning plays an important role in the identification of the relevant features in the spectrogram. The intricate patterns in the time and frequency domains are represented through CNN and RNN. These models are trained and tested through a large dataset which includes both clean and noisy speech samples. This helps to learn complex interrelationships and patterns associated with varied environmental conditions and interference systems. The computational demands of these systems are handled through the cloud computing techniques. They provide a platform for effective solutions for performing real-time interference. These cloud services provide various collaborations to numerous models to achieve desired outcomes. The proposed system provides higher adaptability in varied environmental and noisy profiles. Thus the integration of cloud computing with machine learning provides real-time processing with a natural seamless user experience.

关键词： Cloud computing Time-frequency analysis Visualization Computational modeling Machine learning Interference Speech enhancement

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：