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

2,952 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

2,998 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...
164 篇 deep learning
135 篇 computational mo...
124 篇 feature extracti...
115 篇 neural network
114 篇 convolutional ne...
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
74 篇 computer archite...
73 篇 distributed comp...
65 篇 signal processin...
62 篇 distributed proc...
62 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

2,943 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 2998 条记录，以下是451-460 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：

Quantum-Train with Tensor network Mapping Model and distributed Circuit Ansatz

Quantum-Train with Tensor Network Mapping Model and Distribu...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Chen-Yu Liu Chu-Hsuan Abraham Lin Kuan-Cheng Chen Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Department of Electrical and Electronic Engineering Imperial College London London UK Centre for Quantum Engineering Science and Technology (QuEST) Imperial College London London UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the Quantum-Train (QT) framework, mapping quantum state measurements to classical neural network weights is a critical challenge that affects the scalability and efficiency of hybrid quantum-classical models. The traditional QT framework employs a multi-layer perceptron (MLP) for this task, but it struggles with scalability and interpretability. To address these issues, we propose replacing the MLP with a tensor network-based model and introducing a distributed circuit ansatz designed for large-scale quantum machine learning with multiple small quantum processing unit nodes. This approach enhances scalability, efficiently represents high-dimensional data, and maintains a compact model structure. Our enhanced QT framework retains the benefits of reduced parameter count and independence from quantum resources during inference. Experimental results on benchmark datasets demonstrate that the tensor network-based QT framework achieves competitive performance with improved efficiency and generalization, offering a practical solution for scalable hybrid quantum-classical machine learning.

关键词： Weight measurement Tensors Quantum computing High dimensional data Scalability neural networks Signal processing Quantum state Integrated circuit modeling Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Survey of Class Activation Mapping for the Interpretability of Convolution neural networks 10th

A Survey of Class Activation Mapping for the Interpretabilit...

引用

10th International conference on Signal and Information processing, network and Computers, ICSINC 2022

作者： He, Mingwei Li, Bohan Sun, Songlin Beijing University of Posts and Telecommunications Beijing100876 China School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9789811999673

Recent advances in deep learning have brought a new era for many fields, including object identification, image classification, and image compression. These tasks mostly build models based on the convolutional neural network (CNN). The trained models provide "input-output" end-to-end solutions with excellent automatic feature extraction performance. On the other hand, due to the distributed feature coding and the growing complexity of the model structure, users cannot comprehend the model’s internal knowledge representation and the potential reasons for a particular decision. However, applying CNN models in high-risk areas requires a thorough understanding of the reason behind their decisions in order to earn users’ trust. Therefore, CNN’s interpretation capabilities have gradually gained attention. This survey reviews the literature on class activation mapping (CAM), a straightforward technique for interpreting deep neural networks. We summarize the traditional CAM method and related methods based on the traditional model and then discuss new frontiers. This review can provide researchers in the field of CAM with guidance and, hopefully, shed light on future research regarding the interpretability of CNNs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

neural Analogical Reasoning 16

Neural Analogical Reasoning

引用

16th International Workshop on neural-Symbolic Learning and Reasoning (NeSy) as part of the 2nd International Joint conference on Learning and Reasoning (IJCLR)

作者： Sonwane, Atharv Lalwani, Abhinav Mahajan, Sweta Shroff, Gautam Vig, Lovekesh BITS Pilani APPCAIR KK Birla Goa Campus Sancoale India Indian Inst Technol Delhi India TCS Res New Delhi India

Symbolic systems excel at reusing and composing modular functional units when solving problems such as simple analogical reasoning. However, they are less amenable to processing real-world data (e.g. images), and rely on additional (often hard-coded) mechanisms to convert such high-dimensional data to symbolic descriptions. In this work, we describe a modular approach 'neural Analogical Reasoning' wherein elementary neural transformations operate and compose on distributed representations of high-dimensional inputs. We apply this approach on a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input-output images are related, so as to analogously transform future inputs. This can be viewed as a program synthesis task and solved via symbolic search if represented in symbolic form. Instead, we search for a sequence of elementary neural network transformations that manipulate distributed representations of the inputs. We present two variations of learning useful representations for this task and compare both with end-to-end meta-learning based approaches to demonstrate the importance of performing an explicit search.

关键词： neural reasoning visual analogy making

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digit Recognition Based on Deep Learning Algorithms

Handwritten Digit Recognition Based on Deep Learning Algorit...

引用

2023 International conference on Internet of Things, Robotics and distributed Computing, ICIRDC 2023

作者： Lv, Xue Wuhan Donghu University Hubei Wuhan430212 China

ISBN: (纸本)9798350375275

In the digital age, handwritten digit recognition plays a crucial role in various automation systems, ranging from simple form data automation to complex security systems. Deep learning, particularly Convolutional neural networks (CNNs), has emerged as a leading technology for enhancing the performance of these systems. This article begins by introducing the application background of deep learning in handwritten digit recognition, highlighting the importance and practical applications of this field. It then delves into the fundamental principles of deep learning, focusing on CNNs and how they adapt to the task of recognizing handwritten digits. The discussion also covers different types of neural network architectures and how they optimize performance based on the diversity and complexity of handwriting styles. Additionally, the article explores the importance of data preprocessing, including image normalization, denoising, and augmentation, which are crucial steps in improving model accuracy and robustness. In the experimental section, various CNN architectures are employed and trained and tested using standard handwritten digit datasets. Through detailed experiments and comparative analysis, the performance of different models in terms of recognition accuracy, processing speed, and generalization capabilities is demonstrated. The results reveal the efficiency and accuracy of certain specific CNN models in handling complex handwriting styles, while also highlighting the limitations of some models under specific conditions. In conclusion, the article summarizes the prospects of deep learning in the field of handwritten digit recognition, emphasizing the necessity of continuing to research and develop more advanced algorithms. Future research directions, such as combining deep learning techniques with other machine learning methods to enhance the generalization and adaptability of models, are also discussed. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

splitDyn: Federated Split neural network for distributed Edge AI Applications

splitDyn: Federated Split Neural Network for Distributed Edg...

引用

2022 IEEE International conference on Big Data, Big Data 2022

作者： Khoa, Tran Anh Nguyen, Do-Van Dao, Minh-Son Zettsu, Koji National Institute of Information and Communications Technology Big Data Integration Research Center Tokyo Japan

ISBN: (纸本)9781665480451

Split learning (SL) is a popular distributed machine learning (ML) method used to enable ML. It divides a neural network based model into subnetworks. Then, it separately trains the subnetworks on distributed parties (e.g., client and server). In distributed ML, data are generated and collected on the client-side. In contrast, the collected data are processed using an application deployed on the server side. However, when applied in practice using Internet of things systems and clients, numerous obstacles occur because of limited configuration and resources. Dividing neural networks in the SL is the biggest problem and an open question in numerous studies. This study introduces splitDyn, which is a new dynamic SL solution to solve the aforementioned problems. This method provides a solution for eliminating their inherent drawbacks. The main idea is to apply a Round-Robin schedule to select the client for the training process. Then, the next idea is to use the Hungarian optimization algorithm to assign a layer to a client and enhance the accuracy. The proposed method reasonably achieved better accuracy and reduced processing time than the other learning models. Furthermore, it applies the incident datasets to predict the incident event and in edge computing for edge artificial intelligence (AI) applications. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Domain-Aware Model Training as a Service for Use-Inspired Models 12

Domain-Aware Model Training as a Service for Use-Inspired Mo...

引用

12th International conference on Cloud Engineering

作者： Zhang, Zichen Stewart, Christopher Ohio State Univ Columbus OH 43210 USA

ISBN: (纸本)9798331528690;9798331528706

Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously using compact and efficient model architectures needed for inference in the field. However, before settling upon a model, domain experts repeatedly train and test models over a wide range of hyperparameters, contextual settings, and data configurations, making model training bespoke, time-consuming, and costly. Model-training-as-a-Service (MTaaS), i.e., cloud services designed for generic training workloads, can reduce training costs, but domain-aware designs and runtime adaptations could yield further reductions. This paper characterizes the potential for domain-aware design and runtime adaptation for MTaaS in digital agriculture. First, we studied the time to train models for 10 use-inspired agricultural datasets using pre-trained model weights derived from other agricultural datasets versus pre-trained weights derived from ImageNet, a widely used benchmark. Using agricultural datasets sped training time by up to 2X for some datasets, but provided modest speedups (< 1.07) in the common case;Choosing the right dataset is critical. Next, we present an approach to predict training time given domain-aware pre-trained weights. Our predictions are strongly correlated with training time (r = 0.93). Finally, we studied the use of domain-aware pre-trained weights in a MTaaS under Poisson and bursty arrival patterns for training tasks. Under bursty arrivals and tight memory constraints, domain-aware MTaaS reduced training time by 2.8X and 12.2X compared to model training using pre-trained ImageNet weights and from scratch, respectively.

关键词： Transfer Learning Cloud Service Dataset Similarity neural network distributed System Model-Training-as-a-Service

来源：评论

学校读者我要写书评

暂无评论

ADE-HGNN: Accelerating HGNNs Through Attention Disparity Exploitation 30th

ADE-HGNN: Accelerating HGNNs Through Attention Disparity Exp...

引用

30th European conference on Parallel and distributed processing (Euro-Par)

作者： Han, Dengke Wu, Meng Xue, Runzhen Yan, Mingyu Ye, Xiaochun Fan, Dongrui Chinese Acad Sci SKLP Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9783031697654;9783031697661

Heterogeneous Graph neural networks (HGNNs) have recently demonstrated great power in handling heterogeneous graph data, rendering them widely applied in many critical real-world domains. Most HGNN models leverage attention mechanisms to significantly improve model accuracy, albeit at the cost of increased computational complexity and memory bandwidth requirements. Fortunately, the attention disparity from source vertices towards a common target vertex unveils an opportunity to boost the model execution performance by pruning unimportant source vertices during neighbor aggregation. In this study, we commence with a quantitative analysis of the attention disparity in HGNN models, where the importance of different source vertices varies for the same target vertex. To fully exploit this finding for inference acceleration, we propose a runtime pruning method based on min-heap and map it to a dedicated hardware pruner to discard unimportant vertices. Given that the pruning overhead itself is non-negligible and cannot be amortized by conventional staged execution paradigm, an operation-fusion execution flow of HGNNs is introduced to overlap the pruning overhead while harnessing inter-stage parallelism. Finally, we present the design of a novel HGNN accelerator, ADE-HGNN, tailored to support the proposed execution framework. Our experimental results demonstrate that ADE-HGNN achieves an average performance improvement of 28.21x over the NVIDIA GPU T4 platform and 7.98x over the advanced GPU A100, with the inference accuracy loss kept within a negligible range of 0.11%similar to 1.47%. Furthermore, ADE-HGNN significantly reduces energy consumption to 1.97% and 5.37% of the two platforms, respectively.

关键词： Heterogeneous Graph neural network HGNN Accelerator Vertex Pruning Operation Fusion

来源：评论

学校读者我要写书评

暂无评论

Applications of Large-Scale Quantum neural networks Based on distributed Quantum Computing

Applications of Large-Scale Quantum Neural Networks Based on...

引用

International conference on Wireless Communications and Signal processing (WCSP)

作者： Yin Kan Junyuan He Cheng Xue AHU-IAI AI Joint Laboratory Anhui University Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei Hefei China Institute of Artificial Intelligence Comprehensive National Science Center Hefei China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

This research investigates the limitations of current quantum hardware in fulfilling the computational demands of quantum neural networks. It introduces an optimized circuit computed method leveraging bit splitting within the framework of distributed quantum computing. The research exemplifies this approach by decomposing a 25-qubit variational quantum circuit into several smaller 5-qubit circuits, thereby enabling distributed quantum computations. A hybrid quantum-classical neural network architecture employing this methodology was implemented and evaluated on selected computer vision datasets. The results were promising, affirming the viability of the approach. The successful implementation of this architecture suggests that future distributed quantum computing systems will likely consist of scalable, heterogeneous quantum systems interconnected through an extensive quantum network. This configuration is anticipated to significantly enhance computational power and versatility, expanding the scope of quantum computing applications in real-world scenarios. This advancement not only validates the feasibility of distributed quantum architectures but also underscores their potential to revolutionize various technological domains through enhanced computational capabilities.

关键词： Wireless communication Quantum computing Data analysis Accuracy neural networks Computer architecture Medical diagnosis Resource management Quantum circuit Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

QRELATION: AN AGENT RELATION-BASED APPROACH FOR MULTI-AGENT REINFORCEMENT LEARNING VALUE FUNCTION FACTORIZATION 47

QRELATION: AN AGENT RELATION-BASED APPROACH FOR MULTI-AGENT ...

引用

47th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Shen, Siqi Liu, Jun Qiu, Mengwei Liu, Weiquan Wang, Cheng Fu, Yongquan Wang, Qinglin Qiao, Peng Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart Cities Xiamen Peoples R China Natl Univ Def Technol Parallel & Distributed Proc Lab Changsha Peoples R China

ISBN: (纸本)9781665405409

The Centralized Training with Decentralized Execution paradigm (CTDE), which trains policies centrally with additional information, is important for Multi-Agent Reinforcement Learning (MARL). For CTDE, value function factorization methods make use of state during training and factorize the value function into multiple local value functions for decentralized execution. These approaches do not fully consider the relational information among agents, resulting in sub-optimal models for complex tasks. To remedy this issue, we propose QRelation which is a graph neural network approach for value function factorization. It considers both the static relations (e.g., agent types) and dynamic relations (e.g., close-by). We show that QRelation can obtain better results than state-of-the-art methods on challenging StarCraft II benchmarks.

关键词： Training conferences Reinforcement learning Benchmark testing Signal processing Graph neural networks Acoustics

来源：评论

学校读者我要写书评

暂无评论

HIANet: Hierarchical Interweaved Aggregation network for Crowd Counting 28th

HIANet: Hierarchical Interweaved Aggregation Network for Cro...

引用

28th International conference on neural Information processing

作者： Xie, Jinyang Zheng, Jinfang Gu, Lingyu Lyu, Chen Lyu, Lei Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China Shandong Prov Key Lab Distributed Comp Software N Jinan 250358 Peoples R China

ISBN: (纸本)9783030923099;9783030923105

Aiming at scale variation in crowd counting, we consider that an optimal solution is to take full advantage of the complementarity between multi-scale features. To implement this idea, we devise a Hierarchical Interweaved Aggregation network (HIANet) in this paper. Instead of directly using the traditional concatenation method to aggregate multi-level features, our Hierarchical Interweaved Aggregation Module (HIAM) utilizes an innovative multiplication aggregation strategy to facilitate sufficient multi-scale feature fusion, which can help HIANet recover more structural and detail information. Furthermore, our HIANet employs a Gated Passing Mechanism (GPM) to selectively control the passing of feature information on each level, thus further to suppress the useless background information. Extensive experiments in different crowd scenes well demonstrate that our method has clear advantages under different evaluation metrics.

关键词： Crowd counting Multi-level feature Computer vision Deep learning

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300页 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：