检索结果-内蒙古大学图书馆

作者： Ma, Yuzhe Zhong, Wei Hu, Shuxiang Gao, Jhih-Rong Kuang, Jian Miao, Jin Yu, Bei Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Hong Kong International School of Information Science and Engineering Dalian University of Technology Dalian China DSG Group Cadence Design Systems San JoseCA United States

In advanced technology nodes, layout decomposition (LD) and mask optimization (MO) are two key stages in integrated circuit design. Due to the inconsistency of the objectives of these two stages, the performance of conventional layout and MO may be suboptimal. To tackle this problem, in this article, we propose a unified framework, which seamlessly integrates LD and MO. We propose a gradient-based approach to solve the unified mathematical formulation, as well as a set of discrete optimization techniques to avoid being stuck in local optimum. The conventional optimization process can be accelerated as some inferior decomposition results can be smartly pruned in early stages. The experimental results show that the proposed unified framework can achieve more than 34times speed-up compared with the conventional two-stage flow, meanwhile, it can dramatically reduce EPE violations by more than 8times , and thus maintain better design quality. © 1982-2012 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Offloading safety- And mission-critical tasks via unreliable connections 32

Offloading safety- And mission-critical tasks via unreliable...

引用

32nd Euromicro Conference on Real-Time systems, ECRTS 2020

作者： Schönberger, Lea Chen, Kuan-Hsun Youssef, Hazem Wietfeld, Christian Chen, Jian-Jia von der Brüggen, Georg Sliwa, Benjamin Venkatapathy, Aswin Karthik Ramachandran ten Hompel, Michael Design Automation for Embedded Systems Group Faculty of Computer Science TU Dortmund University Germany Material Handling and Warehousing Faculty of Mechanical Engineering TU Dortmund University Germany Communication Networks Institute Faculty of Electrical Engineering TU Dortmund University Germany

ISBN: (纸本)9783959771528

For many cyber-physical systems, e.g., IoT systems and autonomous vehicles, offloading workload to auxiliary processing units has become crucial. However, since this approach highly depends on network connectivity and responsiveness, typically only non-critical tasks are offloaded, which have less strict timing requirements than critical tasks. In this work, we provide two protocols allowing to offload critical and non-critical tasks likewise, while providing different service levels for non-critical tasks in the event of an unsuccessful offloading operation, depending on the respective system requirements. We analyze the worst-case timing behavior of the local cyber-physical system and, based on these analyses, we provide a sufficient schedulability test for each of the proposed protocols. In the course of comprehensive experiments, we show that our protocols have reasonable acceptance ratios under the provided schedulability tests. Moreover, we demonstrate that the system behavior under our proposed protocols is strongly dependent on probability of unsuccessful offloading operations, the percentage of critical tasks in the system, and the amount of offloaded workload. © Lea Schönberger, Georg von der Brüggen, Kuan-Hsun Chen, Benjamin Sliwa, Hazem Youssef, Aswin Ramachandran, Christian Wietfeld, Michael ten Hompel, and Jian-Jia Chen.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

On the bias-variance-cost tradeoff of stochastic optimization 21

On the bias-variance-cost tradeoff of stochastic optimizatio...

引用

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

作者： Yifan Hu Xin Chen Niao He UIUC and Department of Industrial and Enterprise Systems Engineering University of Illinois at Urbana-Champaign ETH Zürich and Optimization and Decision Intelligence (ODI) Group Department of Computer Science ETH Zürich

ISBN: (纸本)9781713845393

We consider stochastic optimization when one only has access to biased stochastic oracles of the objective, and obtaining stochastic gradients with low biases comes at high costs. This setting captures a variety of optimization paradigms widely used in machine learning, such as conditional stochastic optimization, bilevel optimization, and distributionally robust optimization. We examine a family of multi-level Monte Carlo (MLMC) gradient methods that exploit a delicate trade-off among the bias, the variance, and the oracle cost. We provide a systematic study of their convergences and total computation complexities for strongly convex, convex, and nonconvex objectives, and demonstrate their superiority over the naive biased stochastic gradient method. Moreover, when applied to conditional stochastic optimization, the MLMC gradient methods significantly improve the best-known sample complexity in the literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AADNet: An End-to-End Deep Learning Model for Auditory Attention Decoding

arXiv

引用

arXiv 2024年

作者： Nguyen, Nhan Duc Thanh Phan, Huy Geirnaert, Simon Mikkelsen, Kaare Kidmose, Preben Center for Ear-EEG Department of Electrical and Computer Engineering Aarhus University Aarhus N8200 Denmark Amazon CambridgeMA02142 United States Stadius Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven and Leuven.AI - KU Leuven institute for AI Kasteelpark Arenberg 10 LeuvenB-3001 Belgium The Department of Neurosciences Research Group ExpORL Herestraat 49 box 721 LeuvenB-3000 Belgium

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone continuous development, driven by its promising application in neuro-steered hearing devices. Most AAD algorithms are relying on the increase in neural entrainment to the envelope of attended speech, as compared to unattended speech, typically using a two-step approach. First, the algorithm predicts representations of the attended speech signal envelopes;second, it identifies the attended speech by finding the highest correlation between the predictions and the representations of the actual speech signals. In this study, we proposed a novel end-to-end neural network architecture, named AADNet, which combines these two stages into a direct approach to address the AAD problem. We compare the proposed network against the traditional approaches, including linear stimulus reconstruction, canonical correlation analysis, and an alternative non-linear stimulus reconstruction using two different datasets. AADNet shows a significant performance improvement for both subject-specific and subject-independent models. Notably, the average subject-independent classification accuracies from 56.1% to 82.7% with analysis window lengths ranging from 1 to 40 seconds, respectively, show a significantly improved ability to generalize to data from unseen subjects. These results highlight the potential of deep learning models for advancing AAD, with promising implications for future hearing aids, assistive devices, and clinical assessments. © 2024, CC BY-NC-SA.

关键词： Hearing aids

来源：评论

学校读者我要写书评

暂无评论

Towards Purposeful Design Space Exploration of Heterogeneous CGRAs: Clock Frequency Estimation

Towards Purposeful Design Space Exploration of Heterogeneous...

引用

Design Automation Conference

作者： Dennis Leander Wolf Christoph Spang Christian Hochberger Department for Electrical Engineering and Information Technology Computer Systems Group TU Darmstadt Department of Computer Science TU Darmstadt

ISBN: (数字)9781728110851

ISBN: (纸本)9781728158020

Coarse Grained Reconfigurable Arrays become increasingly popular. Besides research on scheduling algorithms and microarchitecture concepts, the use of heterogeneous structures can be a key approach to exploit their full potential. Unfortunately, a purposeful design space exploration of CGRAs is not trivial, since one needs to know the clock frequency of the resulting hardware implementation. This paper discusses challenges and a statistical approach to maximum clock frequency estimation of heterogeneous CGRAs with an irregular interconnect on FPGAs. The presented approach allows estimation with a maximum error of 8.8 - 17.4% and a mean error of only 1.9 - 4.6%.

关键词： Clocks Estimation Radio frequency Frequency estimation Field programmable gate arrays Timing Context

来源：评论

学校读者我要写书评

暂无评论

Information Fusion-2-Text: Explainable Aggregation via Linguistic Protoforms 18th

Information Fusion-2-Text: Explainable Aggregation via Lingu...

引用

18th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based systems, IPMU 2020

作者： Murray, Bryce J. Anderson, Derek T. Havens, Timothy C. Wilkin, Tim Wilbik, Anna Electrical Engineering and Computer Science Department University of Missouri ColumbiaMO United States College of Computing and Department of Electrical and Computer Engineering Michigan Technological University HoughtonMI United States School of Information Technology Deakin University GeelongVIC Australia Information Systems Group of the Department of Industrial Engineering and Innovation Sciences Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9783030501525

Recent advancements and applications in artificial intelligence (AI) and machine learning (ML) have highlighted the need for explainable, interpretable, and actionable AI-ML. Most work is focused on explaining deep artificial neural networks, e.g., visual and image captioning. In recent work, we established a set of indices and processes for explainable AI (XAI) relative to information fusion. While informative, the result is information overload and domain expertise is required to understand the results. Herein, we explore the extraction of a reduced set of higher-level linguistic summaries to inform and improve communication with non-fusion experts. Our contribution is a proposed structure of a fusion summary and method to extract this information from a given set of indices. In order to demonstrate the usefulness of the proposed methodology, we provide a case study for using the fuzzy integral to combine a heterogeneous set of deep learners in remote sensing for object detection and land cover classification. This case study shows the potential of our approach to inform users about important trends and anomalies in the models, data and fusion results. This information is critical with respect to transparency, trustworthiness, and identifying limitations of fusion techniques, which may motivate future research and innovation. © 2020, Springer Nature Switzerland AG.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Bridging the diversity gap: Actions and experiences fostering diversity in STEM 8

Bridging the diversity gap: Actions and experiences fosterin...

引用

8th International Conference on Technological Ecosystems for Enhancing Multiculturality, TEEM 2020

作者： García-Holgado, Alicia Gonzalez-González, Carina S. Peixoto, Aruquia Caballero-Gil, Pino Plaza-Merino, Pedro Computer Science Department Grial Research Group Research Institute for Educational Sciences University of Salamanca Salamanca Spain Department of Computer Engineering and Systems University of la Laguna Tenerife Spain Codib CEFET/RJ Nova Iguaçu Brazil Dieectqai Uned Madrid Spain

ISBN: (纸本)9781450388504

This special track about diversity and inclusion in STEM celebrated in Salamanca, Spain, includes ten accepted papers presented in the framework of the 8th edition of the Technological Ecosystems for Enhancing Multiculturality (TEEM 2020) held online in Salamanca, Spain, from October 21th to October 23th, 2020. These papers discuss the diversity gap in Science, Technology, engineering and Mathematics (STEM), with special emphasis in the gender gap and the diversity related to sexual orientation. The track was organized as a roundtable focused on diversity in STEM with the participation of the authors, chairs and two invited experts. © 2020 ACM.

关键词： Inclusions

来源：评论

学校读者我要写书评

暂无评论

Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting

arXiv

引用

arXiv 2023年

作者： Jin, Ming Shi, Guangsi Li, Yuan-Fang Xiong, Bo Zhou, Tian Salim, Flora D. Zhao, Liang Wu, Lingfei Wen, Qingsong Pan, Shirui School of Information and Communication Technology Griffith University Gold Coast Australia Department of Data Science and AI Monash University Melbourne Australia International Max Plank Research School for Intelligent Systems The University of Stuttgart Stuttgart Germany Alibaba Group Hangzhou China School of Computer Science and Engineering University of New South Wales Sydney Australia Department of Computer Science Emory University Atlanta United States Anytime.AI New York United States Squirrel Ai Learning Bellevue United States

Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and their expressive power is bounded by our extended first-order Weisfeiler-Leman algorithm on discrete-time dynamic graphs. To make our findings useful in practice on valid instantiations, we discuss related constraints in detail and outline a theoretical blueprint for designing spatial and temporal modules in spectral domains. Building on these insights and to demonstrate how powerful spectral-temporal GNNs are based on our framework, we propose a simple instantiation named Temporal Graph Gegenbauer Convolution (TGGC), which significantly outperforms most existing models with only linear components and shows better model efficiency. Our findings pave the way for devising a broader array of provably expressive GNN-based models for time series. © 2023, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Motivation in Dynamical Control systems

arXiv

引用

arXiv 2022年

作者： Tiomkin, Stas Nemenman, Ilya Polani, Daniel Tishby, Naftali Computer Engineering Department Charles W. Davidson College of Engineering San Jose State University CA95192 United States Department of Physics Emory University AtlantaGA30322 United States Department of Biology Emory University AtlantaGA30322 United States Initiative in Theory and Modeling of Living Systems Emory University AtlantaGA30322 United States Adaptive Systems Research Group University of Hertfordshire Hatfield United Kingdom The Rachel and Selim Benin School of Computer Science and Engineering Hebrew University of Jerusalem 96906 Israel Hebrew University of Jerusalem 96906 Israel

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an information-theoretic approach to intrinsic motivation, based on maximizing an agent’s empowerment (the mutual information between its past actions and future states). We show that this approach generalizes previous attempts to formalize intrinsic motivation, and we provide a computationally efficient algorithm for computing the necessary quantities. We test our approach on several benchmark control problems, and we explain its success in guiding intrinsically motivated behaviors by relating our information-theoretic control function to fundamental properties of the dynamical system representing the combined agent-environment system. This opens the door for designing practical artificial, intrinsically motivated controllers and for linking animal behaviors to their dynamical properties. © 2022, CC BY-SA.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Energy Disaggregation from Low Sampling Frequency Measurements Using Multi-Layer Zero Crossing Rate

Energy Disaggregation from Low Sampling Frequency Measuremen...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Pascal A. Schirmer Iosif Mporas Communications and Intelligent Systems Group School of Engineering and Computer Science University of Hertfordshire Hatfield UK

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Non-Intrusive Load Monitoring aims to disaggregate the energy consumption measurements of a smart-meter from household to device level. Most commercial smart-meters measure at 1 Hz or slightly higher, in order to be able to wirelessly transmit the acquired data to a server for further data analysis. The measured aggregated signal is a low sampling frequency signal, which is prohibitive for spectral analysis based disaggregation. In this article we propose an extension of the zero crossing rate as a time domain measurement of frequency content and compare it to the previously proposed Karhunen Loeve Expansion, in terms of energy disaggregation performance and in terms of computational time. The proposed feature was evaluated on the well-known and widely used REDD database and the experimental results shown that our approach significantly improves the baseline performance and has much lower computational cost than the previously proposed Karhunen Loeve Expansion.

关键词：

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：