检索结果-内蒙古大学图书馆

37th International Conference on Machine Learning, ICML 2020

作者： Pan, Boyuan Yang, Yazheng Liang, Kaizhao Kailkhura, Bhavya Jin, Zhongming Hua, Xian-Sheng Cai, Deng Li, Bo State Key Lab of CAD&CG Zhejiang University China College of Computer Science Zhejiang University China University of Illinois Urbana-Champaign United States Lawrence Livermore National Laboratory United States Alibaba Group

ISBN: (纸本)9781713821120

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e. dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other’s generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Janus faces of dipolar sources in directional near-field coupling with an oriented misalignment

引用

Physical Review A 2024年第3期109卷 033505-033505页

作者： Chenxu Bian Yuhan Zhong Xuhuinan Chen Tony Low Hongsheng Chen Baile Zhang Xiao Lin State Key Laboratory of Extreme Photonics and Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center College of Information Science and Electronic Engineering Zhejiang University Hangzhou 310027 China and International Joint Innovation Center The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China Department of Electrical and Computer Engineering University of Minnesota Minneapolis Minnesota 55455 USA Key Lab of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang Jinhua Institute of Zhejiang University Zhejiang University Jinhua 321099 China and Shaoxing Institute of Zhejiang University Zhejiang University Shaoxing 312000 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences and Centre for Disruptive Photonic Technologies Nanyang Technological University Singapore 637371 Singapore

Directional near-field coupling can enable many applications, such as directional routing, on-chip information processing, and chiral quantum optics. This directional near-field coupling is generally face dependent, since the induced near-field radiation pattern is dependent on which face (e.g., the upper or lower face) of the dipolar source is facing toward the outcoupler. In other words, the dipolar sources in the directional near-field coupling intrinsically have two faces (e.g., Janus faces), whose corresponding near-field coupling strength and coupling directionality might be distinct. Here, we outline a general physical framework to control these Janus faces in the directional near-field coupling and find that they can have the feature of an oriented misalignment. To be specific, the upper and lower radiation patterns of excited surface waves can have the same shape but are misaligned with a twist angle. For example, the twist angle can be any acute angle if the source is composed of a Huygens dipole and an electric dipole, and it can be any obtuse angle if the source is constructed by a circular electric dipole and a magnetic dipole.

关键词： Classical optics Light-matter interaction Metamaterials Near-field optics Photonics Plasmonics

来源：评论

学校读者我要写书评

暂无评论

The diversity and ecological significance of microbial traits potentially involved in B_(12) biosynthesis in the global ocean

引用

mLife 2023年第4期2卷 416-427页

作者： Jiayin Zhou Wei Qin Xinda Lu Yunfeng Yang David Stahl Nianzhi Jiao Jizhong Zhou Jihua Liu Qichao Tu Institute of Marine Science and Technology Shandong UniversityQingdaoChina Joint Lab for Ocean Research and Education at Dalhousie University Shandong University and Xiamen UniversityQingdaoChina School of Biological Sciences University of OklahomaNormanOklahomaUSA Department of Civil and Environmental Engineering Massachusetts Institute of TechnologyCambridgeMassachusettsUSA State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijingChina Department of Civil and Environmental Engineering University of WashingtonSeattleWashingtonUSA Institute of Marine Microbes and Ecospheres Xiamen UniversityXiamenChina Earth and Environmental Sciences Lawrence Berkeley NationalLaboratoryBerkeley CaliforniaUSA Institutefr Environmental Genomics University of OklahomaNormanOklahomaUSA School of Civil Engineering and Environmental Sciences University of OklahomaNormanOklahomaUSA School of Computer Sciences University of OklahomaNormanOklahomaUSA DermBiont Inc. BostonMassachusettsUSA

Cobalamin(B_(12)),an essential nutrient and growth cofactor for many living organisms on Earth,can be fully synthesized only by selected prokaryotes in ***,microbial communities related to B_(12) biosynthesis could serve as an example subsystem to disentangle the underlying ecological mechanisms balancing the function and taxonomic make-up of complex functional *** anchoring microbial traits potentially involved in B_(12) biosynthesis,we depict the biogeographic patterns of B_(12) biosynthesis genes and the taxa harboring them in the global ocean,despite the limitations of detecting de novo B_(12) synthesizers via metagenomes *** the taxonomic and functional composition of B_(12) biosynthesis genes were strongly shaped by depth,differentiating the epipelagic zones from the mesopelagic *** genes related to B_(12) biosynthesis were relatively stably distributed across different oceans,but the taxa harboring them varied considerably,showing clear functional redundancy among microbial *** taxa carrying B_(12) biosynthesis genes in the surface water were influenced by environmental factors such as temperature,oxygen,and ***,the composition of functional genes was only weakly associated with these environmental *** model analyses demonstrated that determinism governed the variations in B_(12) biosynthesis genes,whereas a higher degree of stochasticity was associated with taxonomic *** associations were observed between the chlorophyll a concentration and B_(12) biosynthesis,confirming its importance in primary production in the global *** results of this study reveal an essential ecological mechanism governing the assembly of microbes in nature:the environment selects for function rather than taxonomy;functional redundancy underlies stochastic community assembly.

关键词： B_(12)biosynthesis community assembly functional genes functional redundancy ocean primary production

来源：评论

学校读者我要写书评

暂无评论

Balanced Binary Neural Networks with Gated Residual

Balanced Binary Neural Networks with Gated Residual

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Mingzhu Shen Xianglong Liu Ruihao Gong Kai Han State Key Laboratory of Software Development Environment Beihang University China State Key Lab of Computer Science Institude of Software CAS UCAS

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the accuracy of networks still remains a critical issue. In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short). First, a weight balanced binarization is introduced and thus the informative binary weights can capture more information contained in the activations. Second, for binary activations, a gated residual is further appended to compensate their information loss during the forward process, with a slight overhead. Both techniques can be wrapped as a generic network module that supports various network architectures for different tasks including classification and detection. The experimental results show that BBG-Net performs remarkably well across various network architectures such as VGG, ResNet and SSD with the superior performance over state-of-the-art methods.

关键词： model compression binary neural networks energy-efficient models

来源：评论

学校读者我要写书评

暂无评论

Selective and Multi-Scale Fusion Mamba for Medical Image Segmentation

SSRN

引用

SSRN 2024年

作者： Li, Guangju Huang, Qinghua Wang, Wei Liu, Longzhong School of Computer Science Northwestern Polytechnical University Xian710129 China Northwestern Polytechnical University Xian710072 China Department of Medical Ultrasonics Institute of Diagnostic and Interventional Ultrasound Ultrasomics Artificial Intelligence X-Lab The First Affiliated Hospital of Sun Yat-Sen University Guangzhou510060 China Department of Ultrasound State Key Laboratory of Oncology in South China Guangdong Provincial Clinical Research Center for Cancer Sun Yat-sen University Cancer Center Guangzhou510060 China

Given the high variability in the morphology and size of lesion areas in medical images, accurate medical image segmentation requires both precise positioning of global contours and careful processing of local boundaries. This emphasizes the importance of fusing multi-scale local and global features. However, existing CNN and Transformer-based models are often limited by high parameter counts and complex calculations, making it difficult to efficiently integrate these features. To address this challenge, we proposed two innovative optimization architectures: Selective Fusion Mamba (SF-Mamba) and Multi-Scale Fusion Mamba (MF-Mamba). SF-Mamba can flexibly and dynamically adjust the fusion strategy of local and global features according to the characteristics of the lesions, effectively handling segmentation tasks with variable morphology. MF-Mamba enhances the model's segmentation ability for lesions of different sizes by capturing global information across scales. Based on these two structures, we constructed a lightweight SMM-UNet model, which not only significantly reduces the computational burden (with only 0.038M parameters) but also demonstrates excellent generalization ability and can efficiently adapt to various types of medical images. Extensive tests on the ISIC2017, ISIC2018, and BUSI public datasets show that SMM-UNet achieves excellent segmentation performance with an extremely low parameter cost. © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Proportionate Recursive Maximum Correntropy Criterion Adaptive Filtering Algorithms and their Performance Analysis

arXiv

引用

arXiv 2022年

作者： Qin, Zhen Tao, Jun Yang, Le Jiang, Ming Department of Computer Science and Engineering Ohio State University Columbus43210 United States School of Information Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Underwater Acoustic Signal Processing The Ministry of Education School of Information Science and Engineering Southeast University Nanjing210096 China Department of ECE University of Canterbury Christchurch8020 New Zealand Pengcheng Lab Shenzhen518066 China

The maximum correntropy criterion (MCC) has been employed to design outlier-robust adaptive filtering algorithms, among which the recursive MCC (RMCC) algorithm is a typical one. Motivated by the success of our recently proposed proportionate recursive least squares (PRLS) algorithm for sparse system identification, we propose to introduce the proportionate updating (PU) mechanism into the RMCC, leading to two sparsity-aware RMCC algorithms: the proportionate recursive MCC (PRMCC) algorithm and the combinational PRMCC (CPRMCC) algorithm. The CPRMCC is implemented as an adaptive convex combination of two PRMCC filters. For PRMCC, its stability condition and mean-square performance were analyzed. Based on the analysis, optimal parameter selection in nonstationary environments was obtained. Performance study of CPRMCC was also provided and showed that the CPRMCC performs at least as well as the better component PRMCC filter in steady state. Numerical simulations of sparse system identification corroborate the advantage of proposed algorithms as well as the validity of theoretical analysis. Copyright © 2022, The Authors. All rights reserved.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

A Channel Selection Method for Motor Imagery EEG Based on Fisher Score of OVR-CSP

A Channel Selection Method for Motor Imagery EEG Based on Fi...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Wei Mu Junkongshuai Wang Lu Wang Pengchao Wang Jiaguan Han Lan Niu Jianxiong Bin Lusheng Liu Jing Zhang Jie Jia Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Laboratory for Neural Interface and Brain Computer Interface Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

EEG is widely used in the field of brain computer interfaces. It has the advantages of being non-invasive, easy acquisition, and so on. However, multi-channel EEG signals will bring noise interference and redundant information while improving the resolution, and channel selection can reduce noise signals to obtain more real signals. Therefore, appropriate channel selection is very necessary for BCI system application. This paper proposes a Fisher score calculation method based on OVR-CSP features for channel selection and uses a transformer to classify. The experimental results show that the proposed method achieves 85.54% accuracy in selecting 16.55 channels on the public dataset BCI IV IIa.

关键词： Electrodes Interference Transformers Feature extraction Electroencephalography Brain-computer interfaces Physiology

来源：评论

学校读者我要写书评

暂无评论

Face preference detection task based on EEG energy analysis in the source domain

Face preference detection task based on EEG energy analysis ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Pengchao Wang Junkongshuai Wang Lu Wang Wei Mu Gege Zhan Xueze Zhang Lan Niu Jianxiong Bin Zhiyan Dong Lihua Zhang Jie Jia Zhongxue Gan Xiaoyang Kang MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Shanghai Engineering Research Center of AI & Robotics Institute of AI and Robotics Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China Yiwu Research Institute of Fudan University Yiwu City China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

Facial stimulation can produce specific event-related potential (ERP) component N170 in the fusiform gyrus region. However, the role of the fusiform gyrus region in facial preference tasks is not clear at present, and the current research of facial preference analysis based on EEG signals is mostly carried out in the scalp domain. This paper explores whether the region of the fusiform gyrus is involved in processing face preference emotions in terms of the distribution of energy over the source domain, and finds that the pars orbitalis cortex is most energetically active in the face preference task and that there are significant differences between the left and right *** Relevance— The role of pars orbitalis in facial preference may help doctors determine whether the pars orbitalis cortex is lost in clinical practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Electroencephalogram Signal Analysis: A Mini Review

Generative Adversarial Networks for Electroencephalogram Sig...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Junkongshuai Wang Wei Mu Aiping Wang Lu Wang Jiaguan Han Pengchao Wang Lan Niu Jianxiong Bin Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of AI & Robotics Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

Brain-computer interface (BCI) technology based on electroencephalography (EEG) signals is growing rapidly and attracting widespread attention. However, due to the EEG acquisition methods, the quality and quantity of EEG signals are not able to be guaranteed. To alleviate the problems caused by the lack of data, in this paper, we introduce the applications of EEG signals using generative adversarial networks (GANs) which have shown great performance in image data augmentation and other time series data and then discuss their performance.

关键词： Time series analysis Generative adversarial networks Electroencephalography Brain-computer interfaces Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Distribution of Electrical Stimulation Current of a Minimally Invasive Endovascular Stent-Electrode

Distribution of Electrical Stimulation Current of a Minimall...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Bo Wen Jing Zhang Minjie Wang Lusheng Liu Yuan Zhang Aiping Wang Lu Wang Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of Meta-Medical Academy for Engineering &Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

The implantable brain-computer interface is a kind of brain-computer interaction device. The electrode array implanted in the deep surface of the brain is used to study neural function and medical rehabilitation. Nowadays, the implanted type usually has different degrees of damage to the brain, and the intravascular electrode, as the best technology, has the advantage of no need to drill holes in the brain, and the EEG signal collected is also strong, so it has become a very promising direction. This paper mainly discusses the intravascular use of vascular stent as a carrier, the attachment of the electrode array to the vascular stent, and the multi-physical field simulation of the array in the superior sagittal sinus. By discussing the layout of different electrode arrays and the discussion of grounding electrodes, this paper summarizes a relatively reasonable electrode array layout and a relatively reasonable selection of grounding electrodes.

关键词： Electrodes Electric potential Minimally invasive surgery Grounding Layout Interference Electrical stimulation

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：