检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Tianyu Liang Riley Murray Aydın Buluç James Demmel Electrical Engineering and Computer Science Department UC Berkeley Computational Research Division Lawrence Berkeley National Lab International Computer Science Institute Sandia National Laboratories

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

This work focuses on accelerating the multiplication of a dense random matrix with a (fixed) sparse matrix, which is frequently used in sketching algorithms. We develop a novel scheme that takes advantage of blocking and recomputation (on-the-fly random number generation) to accelerate this operation. The techniques we propose decrease memory movement, thereby increasing the algorithm’s parallel scalability in shared memory architectures. On the Intel Frontera architecture, our algorithm can achieve 2x speedups over libraries such as Eigen and Intel MKL on some examples. In addition, with 32 threads, we can obtain a parallel efficiency of up to 45%.We also present a theoretical analysis for the memory movement lower bound of our algorithm, showing that under mild assumptions, it’s possible to beat the data movement lower bound of general matrix-matrix multiply (GEMM) by a factor of M, where M is the cache size. Finally, we incorporate our sketching method into a randomized algorithm for overdetermined least squares with sparse data matrices. Our results are competitive with SuiteSparse for highly overdetermined problems; in some cases, we obtain a speedup of 10x over SuiteSparse.

关键词： Distributed processing Scalability Instruction sets Memory management Memory architecture Libraries Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Learned Bayesian Cramér-Rao Bound for Unknown Measurement Models Using Score Neural Networks

arXiv

引用

arXiv 2025年

作者： Habi, Hai Victor Messer, Hagit Bresler, Yoram The School of Electrical Engineering Tel Aviv University Tel Aviv6139001 Israel The Department of Electrical and Computer Engineering The Coordinated Science Lab University of Illinois Urbana-Champaign United States

The Bayesian Cramér-Rao bound (BCRB) is a crucial tool in signal processing for assessing the fundamental limitations of any estimation problem as well as benchmarking within a Bayesian frameworks. However, the BCRB cannot be computed without full knowledge of the prior and the measurement distributions. In this work, we propose a fully learned Bayesian Cramér-Rao bound (LBCRB) that learns both the prior and the measurement distributions. Specifically, we suggest two approaches to obtain the LBCRB: the Posterior Approach and the Measurement-Prior Approach. The Posterior Approach provides a simple method to obtain the LBCRB, whereas the Measurement-Prior Approach enables us to incorporate domain knowledge to improve the sample complexity and interpretability. To achieve this, we introduce a Physics-encoded score neural network which enables us to easily incorporate such domain knowledge into a neural network. We study the learning errors of the two suggested approaches theoretically, and validate them numerically. We demonstrate the two approaches on several signal processing examples, including a linear measurement problem with unknown mixing and Gaussian noise covariance matrices, frequency estimation, and quantized measurement. In addition, we test our approach on a nonlinear signal processing problem of frequency estimation with real-world underwater ambient noise. Copyright © 2025, The Authors. All rights reserved.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

A four-dimensional model for the information storage/output of life

引用

Nano Research 2023年第2期16卷 2630-2634页

作者： Bo Song Lei Jiang Key Laboratory of Optical Technology and Instrument for Medicine Ministry of EducationShanghai Key Lab of Modern Optical SystemSchool of Optical-Electrical Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Key Laboratory of Bio-inspired Materials and Interfacial Science Technical Institute of Physics and ChemistryChinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China

A large amount of progress has achieved in neuroscience,however,there is still a lack of reasonable model for the storage/output(S/O)of life *** cyclical motion of cardio-and pulmonary-myocyte is a typical process of the life information S/O,while the opening and closing sites of Ca^(2+)ion channels during the motion can form a genetically programmed time-dependent three-dimensional(3D)*** phenomena indicate a strong correlation of the information S/O model of these myocytes with the time-sequence 3D ***,based on the time-dependent Ca^(2+)fluorescence imaging during the motion of cardio-and pulmonary-myocyte,here we suggest a four-dimensional(4D)code of information S/O model in cell and nervous *** from the fact of pulmonary myocyte motion able to be controlled by brain,it is deduced that the 4D code in brain has a role of controlling muscles through a pathway of the central nervous system,peripheral nervous system,neuromuscular junction,and muscle *** addition,we also suggested the 4D code of non-innate skill that can be programmed by the learning/training of a long time(~3 years),such as walking,writing,painting,sports,speech,singing,and ***,this 4D S/O model is reasonable for the ultralow energy consumption of life information transmission.

关键词： four-dimensional(4D)storage/output model life information cell nervous system

来源：评论

学校读者我要写书评

暂无评论

Striking a Balance: An Optimal Mechanism Design for Heterogenous Differentially Private Data Acquisition for Logistic Regression

arXiv

引用

arXiv 2023年

作者： Anjarlekar, Ameya Etesami, Rasoul Srikant, R. Department of Electrical and Computer Engineering Coordinated Science Lab University of Illinois Urbana-Champaign United States Departments of Industrial and Systems Engineering and Electrical and Computer Engineering The Coordinated Science Lab University of Illinois Urbana-Champaign United States

We address the challenge of solving machine learning tasks using data from privacy-sensitive sellers. Since the data is private, we design a data market that incentivizes sellers to provide their data in exchange for payments. Therefore our objective is to design a mechanism that optimizes a weighted combination of test loss, seller privacy, and payment, striking a balance between building a good privacy-preserving ML model and minimizing payments to the sellers. To achieve this, we first propose an approach to solve logistic regression with known heterogeneous differential privacy guarantees. Building on these results and leveraging standard mechanism design theory, we develop a two-step optimization framework. We further extend this approach to an online algorithm that handles the sequential arrival of sellers. © 2023, CC BY-NC-ND.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Internet of Drones: Novel Applications, Recent Deployments, and Integration

引用

IEEE Internet of Things Magazine 2021年第4期4卷 8-10页

作者： Chamola, Vinay Yu, F. Richard Sikdar, Biplab Kanhere, Salil Guizani, Mohsen Internet of Things Lab at BITS-Pilani India Carleton University Ottawa Canada Department of Electrical and Computer Engineering Singapore Singapore School of Computer Science and Engineering University of New South Wales Sydney Australia Qatar University Computer Science and Engineering Department Qatar

Unmanned aerial vehicles (UAVs), also called drones, are extensively being adopted for a wide variety of applications such as traffic surveillance, disaster management, rescue operations, and environment monitoring. With the adoption of the Internet of Things (IoT), UAV networks are quickly transforming into the Internet of Drones (IoD) paradigm. This has opened up opportunities for the exploration of more sophisticated UAV applications. © 2018 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting 48

ImagineNet: Target Speaker Extraction with Intermittent Visu...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Pan, Zexu Wang, Wupeng Borsdorf, Marvin Li, Haizhou Institute of Data Science Singapore Singapore Nus Department of Electrical and Computer Engineering Singapore Singapore University of Bremen Machine Listening Lab Germany The Chinese University of HongKong Shenzhen Research Institute of Big Data School of Data Science Shenzhen China

ISBN: (纸本)9781728163277

The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use of visual cue is not only feasible, but also effective due to its noise robustness, and becoming popular. However, it is difficult to guarantee that such parallel visual cue is always available in real-world applications where visual occlusion or intermittent communication can occur. In this paper, we study the audio-visual speaker extraction algorithms with intermittent visual cue. We propose a joint speaker extraction and visual embedding inpainting framework to explore the mutual benefits. To encourage the interaction between the two tasks, they are performed alternately with an interlacing structure and optimized jointly. We also propose two types of visual inpainting losses and study our proposed method with two types of popularly used visual embeddings. The experimental results show that we outperform the baseline in terms of signal quality, perceptual quality, and intelligibility. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Delving into the reversal curse: how far can large language models generalize? 24

Delving into the reversal curse: how far can large language ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengkai Lin Zhihang Fu Kai Liu Liang Xie Binbin Lin Wenxiao Wang Deng Cai Yue Wu Jieping Ye State Key Lab of CAD & CG Zhejiang University and Alibaba Cloud Alibaba Cloud Alibaba Cloud and College of Biomedical Engineering & Instrument Science Zhejiang University College of Computer Science and Technology Zhejiang University of Technology School of Software Technology Zhejiang University and Fullong Inc. School of Software Technology Zhejiang University State Key Lab of CAD & CG Zhejiang University

ISBN: (纸本)9798331314385

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when models, having been trained on the fact "A is B", struggle to generalize this knowledge to infer that "B is A". In this paper, we examine the manifestation of the reversal curse across various tasks and delve into both the generalization abilities and the problem-solving mechanisms of LLMs. This investigation leads to a series of significant insights: (1) LLMs are able to generalize to "B is A" when both A and B are presented in the context as in the case of a multiple-choice question. (2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents. For example, this generalization only applies to biographies structured in "[Name] is [Description]" but not to "[Description] is [Name]". (3) We propose and verify the hypothesis that LLMs possess an inherent bias in fact recalling during knowledge application, which explains and underscores the importance of the document structure to successful learning. (4) The negative impact of this bias on the downstream performance of LLMs can hardly be mitigated through training alone. These findings offer a novel perspective on interpreting LLMs' generalization through their intrinsic mechanisms and provide insights for developing more effective learning methods. https://***/alibaba/thinking_***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers 27

Representation Matters for Mastering Chess: Improved Feature...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Czech, Johannes Blüml, Jannis Kersting, Kristian Steingrimsson, Hedinn Artificial Intelligence and Machine Learning Lab TU Darmstadt Germany Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Darmstadt Germany Department of Electrical and Computer Engineering Rice University HoustonTX United States HoustonTX United States

ISBN: (纸本)9781643685489

While transformers have gained recognition as a versatile tool for artificial intelligence (AI), an unexplored challenge arises in the context of chess — a classical AI benchmark. Here, incorporating Vision Transformers (ViTs) into AlphaZero is insufficient for chess mastery, mainly due to ViTs' computational limitations. The attempt to optimize their efficiency by combining MobileNet and NextViT outperformed AlphaZero by about 30 Elo. However, we propose a practical improvement that involves a simple change in the input representation and value loss functions. As a result, we achieve a significant performance boost of up to 180 Elo points beyond what is currently achievable with AlphaZero in chess. In addition to these improvements, our experimental results using the Integrated Gradient technique confirm the effectiveness of the newly introduced features. © 2024 The Authors.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Explorative Study on Motor Interference During Synchronous Human and Robot Arm Movements Under Varied Presence of a Robot Head

Explorative Study on Motor Interference During Synchronous H...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Mertcan Kaya Kolja Kühnlenz Robotics Research Lab Department of Electrical Engineering and Computer Science Coburg University of Applied Sciences and Arts Coburg Germany

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

This paper investigates the influence of a static robot head on deviations of human hand movements from task direction (motor interference) during simultaneous human and robot arm movements using a collaborative robot arm. Synchronous vertical and horizontal human and robot arm movements are conducted in all combinations (within-subjects factors direction and congruency). The presence of the head (head/ no head) is varied as a between-subjects factor. In this first step, only its motionless presence is deliberately focused at, in order to exclude contributions by eye- or head-movement behavior or facial expressions being difficult variables to generalize from. Participants' hands are tracked optically marker-based and deviations from task-related vertical, respectively, horizontal movements are evaluated. In contrast to expectations, results do not show a significant impact of the robot head on motor interference. Thus, there is evidence, that appearance might not be an activating factor for motor interference in HRI.

关键词： Hands Tracking Neurons Humanoid robots Morphology Interference Motors Manipulators Mirrors Robots

来源：评论

学校读者我要写书评

暂无评论

Real-Time Freezing of Gait Detection: Harnessing Advanced AI for Better Mobility

Real-Time Freezing of Gait Detection: Harnessing Advanced AI...

引用

International Conference on e-health Networking, Applications and Services (HealthCom)

作者： Luyao Yang Osama Amin Basem Shihada Networking Lab Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal Saudi Arabia

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

Freezing of Gait (FoG) represents a critical and debilitating symptom of Parkinson's disease, posing significant challenges in patient mobility and safety. Numerous research efforts have focused on predicting the onset of FoG using wearable sensors and computational aids. However, the unpredictability and brief nature of FoG episodes complicate the ability to predict their onset in real-time, rendering timely detection a complex goal. In our study, we employed an Autoencoder-Wavenet network architecture designed to effectively utilize data from triaxial accelerometers and tri-axial gyroscopes positioned at the ankle. This approach allowed for a more nuanced analysis of movement patterns associated with FoG. Our findings indicated that this model successfully achieved a high level of accuracy in detecting FoG, with a specificity of 0.81, and sensitivity of 0.87. Furthermore, the model demonstrated the capability to provide real-time warnings of FoG onset, achieving a specificity of 0.68 and a sensitivity of 0.86. And an accuracy of 0.67 within a 1-second timeframe on the test set. Consequently, these results underscore the potential of our model in contributing to the real-time detection and management of FoG in Parkinson's disease patients.

关键词： Training Sensitivity Accuracy Parkinson's disease Autoencoders Predictive models Real-time systems Wearable devices Wearable sensors Testing

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：