检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,942 篇 会议
39 篇 期刊文献
6 册 图书

馆藏范围

2,987 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,753 篇 工学
- 1,402 篇 计算机科学与技术...
- 683 篇 软件工程
- 488 篇 电气工程
- 394 篇 信息与通信工程
- 200 篇 控制科学与工程
- 130 篇 生物工程
- 78 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 58 篇 机械工程
- 54 篇 仪器科学与技术
- 48 篇 光学工程
- 33 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 安全科学与工程
- 23 篇 材料科学与工程（可...
- 22 篇 化学工程与技术
- 20 篇 测绘科学与技术
- 19 篇 石油与天然气工程
515 篇 理学
- 225 篇 物理学
- 188 篇 数学
- 143 篇 生物学
- 57 篇 统计学（可授理学、...
- 40 篇 系统科学
- 27 篇 化学
203 篇 管理学
- 135 篇 管理科学与工程(可...
- 81 篇 图书情报与档案管...
- 31 篇 工商管理
135 篇 医学
- 112 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
- 20 篇 社会学
18 篇 文学
14 篇 农学
10 篇 教育学
9 篇 经济学
2 篇 军事学

主题

590 篇 neural networks
173 篇 training
167 篇 artificial neura...
163 篇 deep learning
135 篇 computational mo...
122 篇 feature extracti...
115 篇 neural network
113 篇 convolutional ne...
88 篇 machine learning
86 篇 parallel process...
86 篇 neurons
79 篇 deep neural netw...
74 篇 computer archite...
73 篇 distributed comp...
65 篇 signal processin...
62 篇 distributed proc...
61 篇 accuracy
60 篇 recurrent neural...
55 篇 data models
49 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
6 篇 department of co...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,932 篇 英文
47 篇 其他
8 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 2987 条记录，以下是271-280 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Residual network Based Bidirectional Gated Recurrent Unit for Speech Recognition Using Speech Signals 2

Residual Network Based Bidirectional Gated Recurrent Unit fo...

引用

2nd International conference on distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Naga, Raju M. Jayachandran, T. Alzubaidi, Laith H. Mazumder, Debarshi Praveena, Hirald Dwaraka Gst Gitam Department of Cse Karnataka Nagadenahalli India Nandha Engineering College Department of Ece Tamilnadu Erode India The Islamic University Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ai and Ds Bengaluru India School of Engineering Mohan Babu University Erstwhile Sree Vidya Nikethan Engineering College Department of Ece Andhra Pradesh India

ISBN: (纸本)9798350382952

Speech Recognition is challenging research ins speech processing field of research. Different method has available in previous research that attained high accuracy. However, accuracy of speech recognition is not increased because of irrelevant features in recognition stage. In this research, proposed a Residual network based Bidirectional Gated Recurrent Unit (ResNet based Bi-GRU) method for speech recognition using Libri Speech dataset. The signals from data are pre-processed and feature extraction is performed through Mel Frequency Cepstral Coefficients (MFCC) that extract relevant features. Then, the extracted features are fed to classification stage which recognized the speech signals with high accuracy and less error rates. Performance of developed method is evaluated to metrics of Word Error Rate (%), Character Error Rate (CER), accuracy and f1-score. Developed technique obtained less WER of 4.55%, CER of 4.1%, accuracy of 96.71% and f1-score of 96.15% that is effective than existing methods like Recurrent neural network (RNN) -Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM). © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

GRADIENT INVERSION ATTACKS ON ACOUSTIC SIGNALS: REVEALING SECURITY RISKS IN AUDIO RECOGNITION SYSTEMS 49

GRADIENT INVERSION ATTACKS ON ACOUSTIC SIGNALS: REVEALING SE...

引用

2024 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2024

作者： Ovi, Pretom Roy Gangopadhyay, Aryya Center for Real-time Distributed Sensing and Autonomy University of Maryland Baltimore County United States

ISBN: (纸本)9798350344851

With a greater emphasis on data confidentiality and legislation, distributed training and collaborative machine learning algorithms are being developed to protect sensitive private data. Gradient exchange has become a widely used practice in those multi-node machine learning systems. But with the advent of gradient inversion attacks, it is already established that private training data can be revealed from the gradients. Gradient inversion attacks covertly spy on gradient updates and backtrack from the gradients to obtain information about the raw data. Although this attack has been widely studied in computer vision and natural language processing tasks, understanding the impact of this attack on acoustic signals still requires a comprehensive investigation. To the best of our knowledge, we are the first to explore gradient inversion attacks on acoustic signals by extracting the speakers' voices from an audio recognition system. Here, we design a new application of gradient inversion attack to retrieve the audio signal used for training the deep learning model, irrespective of whether the audio has undergone conversion into mel-spectrogram or MFCC representations prior to feed to neural network. Experimental results demonstrate the capability of our attack method to extract the input vectors of the audio data from the gradients, which highlight the security risks in revealing the sensitive audio data from highly secured systems. We also discuss several possible strategies as countermeasures and their effectiveness to prevent the attack. © 2024 IEEE.

关键词： Adversarial attacks Audio Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Generative Adversarial network for Artistic Style Transfer 20

A Lightweight Generative Adversarial Network for Artistic St...

引用

20th International conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Qiao, Ping'an He, Tongtong College of Computer Science Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9798350356328

Currently, image style transfer is one of the hotspots in image processing. Generative adversarial networks have been successfully applied in many fields by virtue of their advantages, and the technology of image style transfer has also seen improvements. However, there are still some problems with the existing artistic style transfer models. For example, the generated images will contain noisy textures, the style and color effects are not ideal, and the model has many parameters, which is easy to cause model breakdown and unstable training. To overcome these problems, an image transfer method that improves the cycleconsistent generative adversarial network (CycleGAN) is presented in this paper. According to its structural characteristics, distributed shift convolution (DSConv) is introduced through the quantized neural network, and the reverse residual block is used to optimize the generator network structure, which can greatly reduce the calculation amount of the model while also improving the model's perception ability and accuracy and the quality of the generated images. Experiments show that the proposed approach can improve the content details of the generated image andthe color effect of the style texture, significantly reduces the number of model parameters, reduces the computational cost, improves the transfer rate, upgrading the model performance, and has strong style transfer capabilities. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Blind-Touch: Homomorphic Encryption-Based distributed neural network Inference for Privacy-Preserving Fingerprint Authentication 38

Blind-Touch: Homomorphic Encryption-Based Distributed Neural...

引用

38th AAAI conference on Artificial Intelligence (AAAI) / 36th conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Choi, Hyunmin Woo, Simon S. Kim, Hyoungshick NAVER Cloud Seongnam South Korea Sungkyunkwan Univ Dept Artificial Intelligence Seoul South Korea Sungkyunkwan Univ Dept Comp Sci & Engn Seoul South Korea

ISBN: (纸本)1577358872

Fingerprint authentication is a popular security mechanism for smartphones and laptops. However, its adoption in web and cloud environments has been limited due to privacy concerns over storing and processing biometric data on servers. This paper introduces Blind-Touch, a novel machine learning-based fingerprint authentication system leveraging homomorphic encryption to address these privacy concerns. Homomorphic encryption allows computations on encrypted data without decrypting. Thus, Blind-Touch can keep finger-print data encrypted on the server while performing machine learning operations. Blind-Touch combines three strategies to efficiently utilize homomorphic encryption in machine learning: (1) It optimizes the feature vector for a distributed architecture, processing the first fully connected layer (FC-16) in plaintext on the client side and the subsequent layer (FC-1) post-encryption on the server, thereby minimizing encrypted computations;(2) It employs a homomorphic encryption-compatible data compression technique capable of handling 8,192 authentication results concurrently;and (3) It utilizes a clustered server architecture to simultaneously process authentication results, thereby enhancing scalability with increasing user numbers. Blind-Touch achieves high accuracy on two benchmark fingerprint datasets, with a 93.6% F1-score for the PolyU dataset and a 98.2% F1-score for the SOKOTO dataset. Moreover, Blind-Touch can match a finger-print among 5,000 in about 0.65 seconds. With its privacy-focused design, high accuracy, and efficiency, Blind-Touch is a promising alternative to conventional fingerprint authentication for web and cloud applications.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Advanced scene text recognition and application for dynamic driving scenes 4

Advanced scene text recognition and application for dynamic ...

引用

4th International conference on Signal Image processing and Communication, ICSIPC 2024

作者： Wang, Jiahao Lu, Yahao Wu, Lianpei School of Information Engineering Guangdong University of Technology Guangzhou510006 China

ISBN: (纸本)9781510682467

In the mobile driving scenario, insufficient data has become a major challenge for the application of scene text recognition models. An alternative to reduce the cost of data annotation is the active learning method, which improves the performance of the model by screening the data with the largest annotation information entropy for training. However, the calibration deviation of modern convolutional neural network is large, and the confidence cannot accurately reflect the real situation of model prediction. In view of the above problems, a scene text recognition framework based on active learning is proposed. The strategy of generating identically distributed heterogeneous data based on anti-aliasing operation is introduced into the framework. A confidence evaluation method based on prediction invariance is proposed. Combined with the active learning method, the confidence of sample prediction is evaluated and corrected. In addition, a text recognition dataset for mobile driving scenarios is established. This method tested SAR, SVTR, and RobustScanner models on the DSO dataset, with accuracy improvements of 11.28%, 15.12%, and 11.66%, respectively. Compared with experiments with randomly annotated data, the accuracy gains of each model were 5.32%, 5.88%, and 6.53%, respectively. The results confirm that this method significantly reduces manual annotation costs while enhancing model performance and robustness. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Prototyping of Low-Cost Configurable Sparse neural processing Unit with Buffer and Mixed-Precision Reshapeable MAC Array 28

Prototyping of Low-Cost Configurable Sparse Neural Processin...

引用

IEEE 28th International conference on Parallel and distributed Systems (IEEE ICPADS)

作者： Wu, Binyi Furtner, Wolfgang Waschneck, Bernd Mayr, Christian Tech Univ Dresden Fac Elect & Comp Engn Dresden Germany Infineon Technol Div Power & Sensor Syst Munich Germany Tech Univ Dresden Ctr Tactile Internet Human In The Loop CeTI Dresden Germany

ISBN: (纸本)9781665473156

More recently, it has become possible to run deep learning algorithms on edge devices such as microcontrollers due to continuous improvements in neural network optimization algorithms such as quantization and neural architecture search. Nonetheless, most of the embedded hardware available today still falls short of the requirements of running deep neural networks. As a result, specialized processors have emerged to improve the inference efficiency of deep learning algorithms. However, most are not for edge applications that require efficient and low-cost hardware. Therefore, we design and prototype a low-cost configurable sparse neural processing Unit (NPU). The NPU has a built-in buffer and a reshapable mixed-precision multiply-accumulator (MAC) array. The computing and memory resources of the NPU are parameterized, and different NPUs can be derived. Besides, users can also configure the NPU at runtime to fully utilize the resources. In our experiments, the 200MHz NPU with only 32 MACs is more than 32 times faster than the 400MHz STM32H7 when inferring MobileNet-V1. Besides, the yielded NPUs can achieve roofline or even beyond roofline performance. The buffer and reshapeable MAC array push the NPU's attainable performance to the roofline, while the feature of supporting sparsity allows the NPU to obtain performance beyond the roofline.

关键词： low-cost configurable neural processing unit mixed-precision sparsity

来源：评论

学校读者我要写书评

暂无评论

Identification of Mangrove Leaf Disease in Deep Convolutional neural network Approach

Identification of Mangrove Leaf Disease in Deep Convolutiona...

引用

2024 International conference on Control and Automation, Electronics, Robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Rahmat, Romi Fadillah Sitompul, Opim Salim Lydia, Maya Silvi Fahmi, Fahmi Almashura, Raska Lubis, Fahrurrozi Universitas Sumatera Utara Department of Information Technology Medan Indonesia Universitas Sumatera Utara Department of Electrical Engineering Medan Indonesia

ISBN: (纸本)9798331511166

Mangrove forests in Indonesia are distributed over many coastal regions, exhibiting significant biodiversity and diverse structural forms. Mangroves serve as a mitigating factor against wave action and intense wind energy resulting from adverse weather conditions. Another purpose of mangroves is to provide as a food source for various marine species. Mangroves consist of many principal components, including roots, stems, leaves, and blooms. For optimal growth, some portions of mangrove plants must be safeguarded from several diseases, whether induced by parasites/pests or by environmental conditions. The leaves of the mangrove are the most vulnerable to disease;yet, pests visible on the leaves are typically inadequately managed, resulting in the plant being immediately removed when all its leaves are infested. This study uses a Deep Convolutional neural network to recognize these pests effectively. The image processing methods used in this study include smoothing and sharpening. The study findings indicate that the used approach effectively identifies mangrove leaf diseases, with an accuracy of 99.2%. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Architectural Vision for Quantum Computing in the Edge-Cloud Continuum

Architectural Vision for Quantum Computing in the Edge-Cloud...

引用

2nd IEEE International conference on Quantum Software (IEEE QSW)

作者： Furutanpey, Alireza Barzen, Johanna Bechtold, Marvin Dustdar, Schahram Leymann, Frank Raith, Philipp Truger, Felix TU Vienna Distributed Syst Grp Vienna Austria Univ Stuttgart Inst Architecture Applicat Syst Stuttgart Germany

ISBN: (纸本)9798350304794

Quantum processing units (QPUs) are currently exclusively available from cloud vendors. However, with recent advancements, hosting QPUs will soon be possible everywhere. Existing work has yet to draw from research in edge computing to explore systems exploiting mobile QPUs, or how hybrid applications can benefit from distributed heterogeneous resources. Hence, this work presents an architecture for Quantum Computing in the edge-cloud continuum. We discuss the necessity, challenges, and solution approaches for extending existing work on classical edge computing to integrate QPUs. We describe how warm-starting allows defining workflows that exploit the hierarchical resources spread across the continuum. Then, we introduce a distributed inference engine with hybrid classical-quantum neural networks (QNNs) to aid system designers in accommodating applications with complex requirements that incur the highest degree of heterogeneity. We propose solutions focusing on classical layer partitioning and quantum circuit cutting to demonstrate the potential of utilizing classical and quantum computation across the continuum. To evaluate the importance and feasibility of our vision, we provide a proof of concept that exemplifies how extending a classical partition method to integrate quantum circuits can improve the solution quality. Specifically, we implement a split neural network with optional hybrid QNN predictors. Our results show that extending classical methods with QNNs is viable and promising for future work.

关键词： Quantum Computing Edge Computing Compute Continuum Split Computing Circuit Cutting Task Partitioning DNN Partitioning Classical-Quantum Hybrid Machine Learning Quantum neural networks Warm-Starting

来源：评论

学校读者我要写书评

暂无评论

Edge Computing-Enabled Lightweight Deep neural network for Real-Time Video Surveillance in Maritime Cyber-Physical Systems 9

Edge Computing-Enabled Lightweight Deep Neural Network for R...

引用

9th International conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Luo, Caofei Wu, Fumin Xiong, Renhao Xu, Guanhua Liu, Wen Maritime Electronics Research Institute Co. Ltd. Ningbo315040 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310058 China School of Navigation Wuhan University of Technology Wuhan430063 China

ISBN: (纸本)9798350376548

With the rapid developments of low-end IoT devices and artificial intelligence (AI), the heterogeneous and dynamic data has been increasing drastically, especially in the era of AI-enabled maritime cyber-physical systems (CPS). It is intractable to provide the efficient and flexible computer vision applications through traditional cloud-centric data processing strategies, which commonly suffer from the limitations, e.g., high cost, high- latency communication, and high occupied storage, etc. To meet these challenges, edge computing has meaningfully evolved into a flexible and powerful distributed architecture. It contributes to improvements in bandwidth savings and response time in practical applications. To guarantee efficient video surveillance in AI-powered maritime CPS, the edge computing-based lightweight deep network (termed ShipNet-YOLOv3), incorporated with Kalman filtering and Hungarian algorithm, is proposed to implement real-time detection and tracking of moving ships. In particular, ShipNet-YOLOv3 adopts Darknet-53 as the backbone network (i.e., feature extractor) with three prediction boxes. The channel pruning and fine-tuning strategy are further introduced to balance the trade-off between computational cost, network size, and detection (or tracking) accuracy. Experimental results on both synthetic and realistic scenarios have illustrated that the proposed method could provide superior ship detection and tracking results under different adverse imaging conditions. It thus has the capacity of promoting real-time video surveillance in AI -enabled maritime CPS. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Communication Efficient distributed Learning for Kernelized Contextual Bandits 36

Communication Efficient Distributed Learning for Kernelized ...

引用

36th conference on neural Information processing Systems (NeurIPS)

作者： Li, Chuanhao Wang, Huazheng Wang, Mengdi Wang, Hongning Univ Virginia Charlottesville VA 22904 USA Oregon State Univ Corvallis OR USA Princeton Univ Princeton NJ USA

ISBN: (纸本)9781713871088

We tackle the communication efficiency challenge of learning kernelized contextual bandits in a distributed setting. Despite the recent advances in communication-efficient distributed bandit learning, existing solutions are restricted to simple models like multi-armed bandits and linear bandits, which hamper their practical utility. In this paper, instead of assuming the existence of a linear reward mapping from the features to the expected rewards, we consider non-linear reward mappings, by letting agents collaboratively search in a reproducing kernel Hilbert space (RKHS). This introduces significant challenges in communication efficiency as distributed kernel learning requires the transfer of raw data, leading to a communication cost that grows linearly w.r.t. time horizon T. We address this issue by equipping all agents to communicate via a common Nystrom embedding that gets updated adaptively as more data points are collected. We rigorously proved that our algorithm can attain sub-linear rate in both regret and communication cost.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共299页 << < 24 25 26 27 28 29 30 31 32 33 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：