检索结果-内蒙古大学图书馆

On the Attractive and Repulsive Forces of Generalized Stochastic Neighbor Embedding With Alpha-Divergence

IEEE Access 2024年 12卷 90380-90394页

作者： Lin, Hsin-Yi Tseng, Huan-Hsin Chien, Jen-Tzung Seton Hall University Department Of Mathematics And Computer Science South OrangeNJ07079 United States Brookhaven National Laboratory Computational Science Initiative UptonNY11973 United States Institute Of Electrical And Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Stochastic neighbor embedding (SNE) performs nonlinear transformation from high-dimensional observation space to low-dimensional latent space which preserves neighbor affinities. Data pairs in latent space tend to be crowded due to the dimensionality reduction. To mitigate the crowding problem, certain characteristics are favorable in the design of the SNE setting. This study presents a fundamental analysis of SNE that not only generalizes the previous SNEs but also provides a systematic way to understand the intrinsic properties. From the perspective of theoretical connection, we are able to conceive a new generalized SNE (g-SNE) by introducing a regularized power-law distribution with the α-divergence for manifold learning. The proposed method generalizes and incorporates various favorable features for the clustering process. In addition, the proposed method provides high flexibility, admitting tailored realizations to properly reflect the similarity between original and dimension-reduced samples. Experiments are performed to analyze the proposed method, and its effectiveness is demonstrated with several learning tasks. © 2024 The Authors.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Registration: Magic or Mirage? 38

Deep Learning in Medical Image Registration: Magic or Mirage...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jena, Rohit Sethi, Deeksha Chaudhari, Pratik Gee, James C. Computer and Information Science United States Electrical and Systems Engineering United States Radiology United States Penn Image Computing and Science Laboratory United States

Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. We reassess and recalibrate performance expectations from classical and DLIR methods under access to label supervision, training time, and its generalization capabilities under minor domain shifts. © 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

Majorizing Measures, Codes, and Information

Majorizing Measures, Codes, and Information

引用

IEEE International Symposium on Information Theory

作者： Yifeng Chu Maxim Raginsky Department of Electrical and Computer Engineering and the Coordinated Science Laboratory University of Illinois Urbana IL USA

The majorizing measure theorem of Fernique and Talagrand is a fundamental result in the theory of random processes. It relates the boundedness of random processes indexed by elements of a metric space to complexity measures arising from certain multiscale combinatorial structures, such as packing and covering trees. This paper builds on the ideas first outlined in a little-noticed preprint of Andreas Maurer to present an information-theoretic perspective on the majorizing measure theorem, according to which the boundedness of random processes is phrased in terms of the existence of efficient variable-length codes for the elements of the indexing metric space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Channel-Feedback-Free Transmission for Downlink FD-RAN:A Radio Map Based Complex-Valued Precoding Network Approach

引用

China Communications 2024年第4期21卷 10-22页

作者： Zhao Jiwei Chen Jiacheng Sun Zeyu Shi Yuhang Zhou Haibo Xuemin(Sherman)Shen School of Electronic Science and Engineering Nanjing UniversityNanjing 210023China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310058China Department of Mathematics and Theories Peng Cheng LaboratoryShenzhen 518000China Department of Electrical and Computer Engineering University of WaterlooWaterlooOntarioN2L 3G1Canada

As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network ***,with the decoupling of uplink base stations and downlink base stations in FDRAN,the traditional transmission mechanism,which relies on real-time channel feedback,is not suitable as the receiver is not able to feedback accurate and timely channel state information to the *** paper proposes a novel transmission scheme without relying on physical layer channel ***,we design a radio map based complex-valued precoding network(RMCPNet)model,which outputs the base station precoding based on user *** comprises multiple subnets,with each subnet responsible for extracting unique modal features from diverse input ***,the multimodal embeddings derived from these distinct subnets are integrated within the information fusion layer,culminating in a unified *** also develop a specific RMCPNet training algorithm that employs the negative spectral efficiency as the loss *** evaluate the performance of the proposed scheme on the public DeepMIMO dataset and show that RMCPNet can achieve 16%and 76%performance improvements over the conventional real-valued neural network and statistical codebook approach,respectively.

关键词： beamforming complex neural networks deep learning FD-RAN

来源：评论

学校读者我要写书评

暂无评论

Learning to Communicate Among Agents for Large-Scale Dynamic Path Planning With Genetic Programming Hyperheuristic

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1269-1283页

作者： Liao, Xiao-Cheng Hu, Xiao-Min Chen, Xiang-Ling Mei, Yi Jia, Ya-Hui Chen, Wei-Neng Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Hanyang University Department of Electrical and Electronic Engineering Ansan15588 Korea Republic of South China University of Technology School of Future Technology Guangzhou510006 China Pazhou Lab Guangzhou510005 China South China University of Technology School of Computer Science and Engineering State Key Laboratory of Subtropical Building and Urban Science Guangzhou510006 China

Genetic programming hyperheuristic (GPHH) has recently become a promising methodology for large-scale dynamic path planning (LDPP) since it can produce reusable heuristics rather than disposable solutions. However, in this methodology, the extracted local and decentralized heuristic for agents that lack a global systemic view sometimes may be problematic. Therefore, a new challenge is to strike a balance between conciseness to improve generalization ability and incorporation of more global information to obtain better performance. In this work, we target the LDPP problem and propose a communication learning mechanism (ComLGP) for GPHH to address the above difficulties. In ComLGP, a communication function is introduced to serve as a communication protocol and exist in the form of an extra terminal in GPHH. Compared to the classic terminals which are fixed in genetic programing, this communication function undergoes optimization along with the evolutionary process of GPHH. In this way, the communication function can be learned which enables agents to communicate without a predefined communication protocol. Then, a caching and lazy updating mechanism for ComLGP is presented to accelerate the calculation of communication content. Last, we verified our method on 22 scenarios including two real world road networks. The experimental results demonstrate that the proposed ComLGP can successfully learn to communicate. Although in the absence of any manually designed communication features, ComLGP is capable of achieving performance competitive to the state-of-the-art method that employs a predefined communication protocol and outperforms the remaining compared methods in most scenarios. © 2020 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Random Real Valued and Complex Valued States Cannot be Efficiently Distinguished

arXiv

引用

arXiv 2024年

作者： Schatzki, Louis Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois at Urbana-Champaign UrbanaIL61801 United States

In this short note we show that the ensemble {O |0〉 〈0| Oт | O ∈ O(d)}, where O is drawn from the Haar_ measure on O(d) cannot be distinguished from t copies of a Haar random state unless t = Ω(√d). Our proof has the benefit of exactly computing the trace distance, which scales as Θ(t2/d) for t = O(√d), between the moments as well as being surprisingly short. Lastly, we show that twirling certain states with orthogonal matrices yields exact t = 3 designs, yet the same cannot be true for t > 3. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Functional plastic films:nano-engineered composite based flexible microwave antennas with near-unity relative visible transmittance

引用

Light(Advanced Manufacturing) 2024年第2期5卷 95-105页

作者： Cheng Zhang Liang Zhu Chengang Ji Zhilu Ye Nabeel Alsaab Minye Yang Yuhui Hu Pai-Yen Chen L.Jay Guo School of Optical and Electronic Information&Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan430074China Department of Electrical and Computer Engineering University of Illinois at ChicagoChicagoIL 60607USA Department of Electrical Engineering and Computer Science University of MichiganAnn ArborMI 48109USA

Microwave antennas are essential elements for various applications,such as telecommunication,radar,sensing,and wireless power *** antennas are conventionally manufactured on rigid substrates using opaque materials,such as metal strips,metallic tapes,or epoxy pastes;thus,prohibiting their use in flexible and wearable devices,and simultaneously limiting their integration into existing optoelectronic ***,we demonstrate that mechanically flexible and optically transparent microwave antennas with high operational efficiencies can be readily fabricated using composite nanolayers deposited on common plastic *** composite nanolayer structure consists of an ultra-thin copper-doped silver film sandwiched between two dielectric films of tantalum pentoxide and aluminum *** material and thickness of each constituent layer are judiciously selected such that the whole structure exhibits an experimentally measured averaged visible transmittance as high as 98.94%compared to a bare plastic substrate,and simultaneously,a sheet resistance as low as 12.5Ω/*** representative types of microwave antennas are implemented:an omnidirectional dipole antenna,unidirectional Yagi-Uda antenna,low-profile patch antenna,and Fabry-Pérot cavity *** devices exhibit great mechanical flexibility with bending angle over 70°,high gain of up to 13.6 dBi,and large radiation efficiency of up to 84.5%.The proposed nano-engineered composites can be easily prepared over large areas on various types of substrates and simultaneously overcome the limitations of poor mechanical flexibility,low electrical conductivity,and reduced optical transparency usually faced by other constituent materials for flexible transparent microwave *** demonstrated flexible microwave antennas have various applications ranging from fifth-generation and vehicular communication systems to bio-signal monitors and wearable electronics.

关键词： Optically transparent antenna Flexible microwave antenna Transparent conductor Ultra-thin silver Doped silver Wearable optoelectronics

来源：评论

学校读者我要写书评

暂无评论

Power-Measurement-Based Channel Autocorrelation Estimation for IRS-Assisted Wideband Communications

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4647-4662页

作者： Sun, He Zhu, Lipeng Mei, Weidong Zhang, Rui National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications 611731 China The Chinese University of Hon g Kong School of Science and Engineering Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China

Channel state information (CSI) is essential to the performance optimization of intelligent reflecting surface (IRS)-aided wireless communication systems. However, the passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed practical challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To tackle the above challenge, we propose a novel neural network (NN)-empowered IRS channel estimation and passive reflection design framework for the wideband orthogonal frequency division multiplexing (OFDM) communication system based only on the user’s reference signal received power (RSRP) measurements with time-varying random IRS training reflections. As RSRP is readily accessible in existing communication systems, our proposed channel estimation method does not require additional pilot transmission in IRS-aided wideband communication systems. In particular, we show that the average received signal power over all OFDM subcarriers at the user terminal can be represented as the prediction of a single-layer NN composed of multiple subnetworks with the same structure, such that the autocorrelation matrix of the wideband IRS channel can be recovered as their weights via supervised learning. To exploit the potential sparsity of the channel autocorrelation matrix, a progressive training method is proposed by gradually increasing the number of subnetworks until a desired accuracy is achieved, thus reducing the training complexity. Based on the estimates of IRS channel autocorrelation matrix, the IRS passive reflection is then optimized to maximize the average channel power gain over all subcarriers. Numerical results indicate the effectiveness of the proposed IRS channel autocorrelation matrix estimation and passive reflection design under wideband channels, which can achieve significant performance improvement compared to the existing IRS re

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Prediction of segregation characterization based on granular velocity and concentration in rotating drum

引用

Particuology 2023年第2期73卷 17-25页

作者： Wenzheng Xiu Ra Li Quan Chen Qicheng Sun Vladimir Zivkovic Hui Yang School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China School of Medical Instrument and Food Engineering University of Shanghai for Science and TechnologyShanghai200093China State Key Laboratory of Hydroscience and Engineering Tsinghua UniversityBeijing100084China School of Engineering Newcastle UniversityNE17RUUnited Kingdom

In a binary granular system composed of two types of particles with different granule sizes and the same density,particle sorting occurs easily during the flow *** segregation pattern structure is mainly affected by the granular velocity and granular concentration in the flow *** paper reports on the experimental velocity and concentration measurement results for spherical particles in a quasi-two-dimensional rotating *** relationship between the granular velocity along the depth direction of the flow layer and granular concentration was established to characterize structures with different degrees of *** corresponding relationships between the granular velocity and concentration and the segregation pattern were further analyzed to improve the theoretical models of segregation(convection-diffusion model and continuous flow model)and provide a reference for granular segregation control in the production process.

关键词： Granular segregation Rotating drum Granular velocity Granular concentration

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：