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

2,958 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,004 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,759 篇 工学
- 1,406 篇 计算机科学与技术...
- 685 篇 软件工程
- 489 篇 电气工程
- 396 篇 信息与通信工程
- 202 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
- 49 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
516 篇 理学
- 225 篇 物理学
- 189 篇 数学
- 143 篇 生物学
- 58 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

2,925 篇 英文
71 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 3004 条记录，以下是1371-1380 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：

A novel deep neural design and efficient Pipeline architecture for Person Re-Identification in high resolution Video

A novel deep neural design and efficient Pipeline architectu...

引用

International Communication Systems and networks and Workshops, COMSNETS

作者： Govardhan Mattela Manmohan Tripathi Chandrajit Pal Indian Institute of Technology (IIT) Hyderabad India Ceremorphic India Pvt Ltd

ISBN: (数字)9781728191270

ISBN: (纸本)9781728191287

The primary objective of person re-identification (Re-ID) is to retrieve a person of interest across different nonintersecting cameras for managing in distributed surveillance systems. This has added to its increasing popularity on account of its widespread use, applications and research significance. In this study, we have proposed a novel pipelined deep learning architecture which acts as a robust feature extractor and also helps in reducing down the search space by generating feature embeddings followed by executing a distance metric measurement for finding the similar neighbourhood embeddings and subsequently sorting the cluster centroids of the matching embeddings for finding a set of the nearest match before passing down to a siamese network for similarity checking in the reidentification process. Our experiments reported to achieve a performance accuracy of 85~90% with a model size of 288 MB executing at 30 fps in real-time.

关键词： Measurement Surveillance Pipelines Graphics processing units Feature extraction Throughput Sorting

来源：评论

学校读者我要写书评

暂无评论

Signal Analysis of distributed Optic-Fiber Sensing Used for Oil and Gas Pipeline Monitoring 2019

Signal Analysis of Distributed Optic-Fiber Sensing Used for ...

引用

International Symposium on Signal processing Systems (SPSS) / International conference on Natural Language processing (ICNLP)

作者： Yang, Yue Li, Jun Tian, Ming Zhou, Yang Dong, Lei He, Jing Xin Wuhan WUTOS CO LTO Univ Pk Rd 23 Eastlake Development Dis Peoples R China Sinopec Pipeline Storage & Transportat Co LTD Xuzhou Quanshan Dist South Rd 1 Xuzhou Jiangsu Peoples R China

ISBN: (纸本)9781450362412

distributed optic-fiber sensing technology based on coherent Rayleigh scattering can use optical fiber cable laying along with pipeline as vibration sensor, to give early-warning of the third-party threaten and even damage on oil and gas pipeline. First, an adaptive filtering is performed on the time-domain signals collected by all sensing units to make the preliminary judgment. Then, an advanced signal process method composed by convolutional neural network is proposed to extract the event areas and judge event categories. Field trial experiment results show that the system can effectively detect digging event with the recognition accuracy up to 97%.

关键词： distributed optic-fiber sensing oil and gas pipeline adaptive filtering image processing convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Limitations of Lazy Training of Two-layers neural networks 33

Limitations of Lazy Training of Two-layers Neural Networks

引用

33rd conference on neural Information processing Systems (NeurIPS)

作者： Ghorbani, Behrooz Mei, Song Misiakiewicz, Theodor Montanari, Andrea Stanford Univ Dept Elect Engn Stanford CA 94305 USA Stanford Univ ICME Stanford CA 94305 USA Stanford Univ Dept Stat Stanford CA 94305 USA

We study the supervised learning problem under either of the following two models: (1) Feature vectors xi are d-dimensional Gaussians and responses are y(i) = f(*) (x(i)) for f(*) an unknown quadratic function;(2) Feature vectors xi are distributed as a mixture of two d-dimensional centered Gaussians, and y(i)'s are the corresponding class labels. We use two-layers neural networks with quadratic activations, and compare three different learning regimes: the random features (RF) regime in which we only train the second-layer weights;the neural tangent (NT) regime in which we train a linearization of the neural network around its initialization;the fully trained neural network (NN) regime in which we train all the weights in the network. We prove that, even for the simple quadratic model of point (1), there is a potentially unbounded gap between the prediction risk achieved in these three training regimes, when the number of neurons is smaller than the ambient dimension. When the number of neurons is larger than the number of dimensions, the problem is significantly easier and both NT and NN learning achieve zero risk.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling a H-H Neuron based Spiking neural network incorporating Multiple Pre-synaptic Inputs 2

Modeling a H-H Neuron based Spiking Neural Network incorpora...

引用

2nd International conference on Innovations in Electronics, Signal processing and Communication, IESC 2019

作者： Gogoi, Plabita Roy, Soumik Bujarbaruah, Satyabrat Malla Tezpur University Department of Electronics and Communication Engineering Tezpur India

ISBN: (纸本)9781728107448

Spiking neural networks (SNN) is the latest generation of Artificial neural networks that draws strength from the capability to closely mimic its biological counterpart. The choice of the spiking neuron that constitutes the core entity of a SNN determines its effectiveness for a particular application. Certain situations such as "neuron replacement therapy" can demand a precise realization of the biological neural net by the bio-mimetic prosthesis. Such specific prerequisites can only be catered using a network comprising of detailed neuron models that encompasses synaptic interactions between multiple neurons. Hence, in the proposed work, a simple spiking neural network is modeled using a "conjoint" neuron model that amalgamates the strengths and versatilities of the H-H model, Integrate-And-Fire model and Synapse model and thus presents a unique representation of the membrane behaviour due to multiple temporally varying and spatially distributed synaptic inputs. © 2019 IEEE.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

MATE: benchmarking multi-agent reinforcement learning in distributed target coverage control 22

MATE: benchmarking multi-agent reinforcement learning in dis...

引用

Proceedings of the 36th International conference on neural Information processing Systems

作者： Xuehai Pan Mickel Liu Fangwei Zhong Yaodong Yang Song-Chun Zhu Yizhou Wang School of Computer Science Peking University and Center on Frontiers of Computing Studies Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) School of Intelligence Science and Technology Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) School of Intelligence Science and Technology Peking University and Institute for Artificial Intelligence Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) School of Intelligence Science and Technology Peking University and Institute for Artificial Intelligence Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) and Department of Automation Tsinghua University School of Computer Science Peking University and Center on Frontiers of Computing Studies Peking University and Institute for Artificial Intelligence Peking University

ISBN: (纸本)9781713871088

We introduce the Multi-Agent Tracking Environment (MATE), a novel multi-agent environment simulates the target coverage control problems in the real world. MATE hosts an asymmetric cooperative-competitive game consisting of two groups of learning agents—"cameras" and "targets"—with opposing interests. Specifically, "cameras", a group of directional sensors, are mandated to actively control the directional perception area to maximize the coverage rate of targets. On the other side, "targets" are mobile agents that aim to transport cargo between multiple randomly assigned warehouses while minimizing the exposure to the camera sensor networks. To showcase the practicality of MATE, we benchmark the multi-agent reinforcement learning (MARL) algorithms from different aspects, including cooperation, communication, scalability, robustness, and asymmetric self-play. We start by reporting results for cooperative tasks using MARL algorithms (MAPPO, IPPO, QMIX, MADDPG) and the results after augmenting with multi-agent communication protocols (TarMAC, I2C). We then evaluate the effectiveness of the popular self-play techniques (PSRO, fictitious self-play) in an asymmetric zero-sum competitive game. This process of co-evolution between cameras and targets helps to realize a less exploitable camera network. We also observe the emergence of different roles of the target agents while incorporating I2C into target-target communication. MATE is written purely in Python and integrated with OpenAI Gym API to enhance user-friendliness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of energy efficient homogenous MPSOC display device trained using NN in FPGA 5

Implementation of energy efficient homogenous MPSOC display ...

引用

5th International conference on Computing, Communication Control and Automation (ICCUBEA)

作者： Khan, Masroor Jadhav, Usha DY Patil Coll Engn Akurdi Elect & Telecommun Pune Maharashtra India

ISBN: (纸本)9781728140421

Artificial neural networks (ANN) are computational models which work similar to human nervous system. Back propagation is one of the method of ANN within Convolutional neural network (CNN) that means "the backward propagation of errors", since an error is computed at the output and distributed backwards throughout the layers. The approach shown trains display devices LED to neural network in FPGA. The Multi Core System On Chip (MPSOC) include multiple microprocessor used in platforms that contain multiple processing elements with specific functionality reflecting the need of the expected application domain, a memory hierarchy and I/O components. The study proposed to minimize the power consumption while meeting the performance needs of the back propagation neural network in MPSOC using display device initially on Single Processor System on Chip (SPSOC) and comparing it to that of energy efficiency of devices over homogenous MPSOC.

关键词： Convolutional neural networks Back Propagation Multi-Processor System On a Chip

来源：评论

学校读者我要写书评

暂无评论

Putting An End to End-to-End: Gradient-Isolated Learning of Representations 33

Putting An End to End-to-End: Gradient-Isolated Learning of ...

引用

33rd conference on neural Information processing Systems (NeurIPS)

作者： Lowe, Sindy O'Connor, Peter Veeling, Bastiaan S. Univ Amsterdam AMLab Amsterdam Netherlands

We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observation that biological neural networks appear to learn without backpropagating a global error signal, we split a deep neural network into a stack of gradient-isolated modules. Each module is trained to maximally preserve the information of its inputs using the InfoNCE bound from Oord et al. [2018]. Despite this greedy training, we demonstrate that each module improves upon the output of its predecessor, and that the representations created by the top module yield highly competitive results on downstream classification tasks in the audio and visual domain. The proposal enables optimizing modules asynchronously, allowing large-scale distributed training of very deep neural networks on unlabelled datasets.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Accelerated Inference Framework of Sparse neural network Based on Nested Bitmask Structure 28

Accelerated Inference Framework of Sparse Neural Network Bas...

引用

28th International Joint conference on Artificial Intelligence

作者： Zhang, Yipeng Du, Bo Zhang, Lefei Li, Rongchun Dou, Yong Wuhan Univ Sch Comp Sci Wuhan Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9780999241141

In order to satisfy the ever-growing demand for high-performance processors for neural networks, the state-of-the-art processing units tend to use application-oriented circuits to replace processing Engine (PE) on the GPU under circumstances where low-power solutions are required. The application-oriented PE is fully optimized in terms of the circuit architecture and eliminates incorrect data dependency and instructional redundancy. In this paper, we propose a novel encoding approach on a sparse neural network after pruning. We partition the weight matrix into numerous blocks and use a low-rank binary map to represent the validation of these blocks. Furthermore, the elements in each nonzero block are also encoded into two submatrices: one is the binary stream discriminating the zero/nonzero position, while the other is the pure nonzero elements stored in the FIFO. In the experimental part, we implement a well pre-trained sparse neural network on the Xilinx FPGA VC707. Experimental results show that our algorithm outperforms the other benchmarks. Our approach has successfully optimized the throughput and the energy efficiency to deal with a single frame. Accordingly, we contend that Nested Bitmask neural network (NBNN), is an efficient neural network structure with only minor accuracy loss on the SoC system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TRAINING DYNAMIC EXPONENTIAL FAMILY MODELS WITH CAUSAL AND LATERAL DEPENDENCIES FOR GENERALIZED NEUROMORPHIC COMPUTING 44

TRAINING DYNAMIC EXPONENTIAL FAMILY MODELS WITH CAUSAL AND L...

引用

44th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Jang, Hyeryung Simeone, Osvaldo Kings Coll London Dept Informat London England

ISBN: (纸本)9781479981311

Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking neural networks (SNNs) as an energy-efficient alternative to Artificial neural networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a probabilistic model is introduced for a generalized set-up in which the synaptic time series can take values in an arbitrary alphabet and are characterized by both causal and instantaneous statistical dependencies. The model, which can be considered as an extension of exponential family harmoniums to time series, is introduced by means of a hybrid directed-undirected graphical representation. Furthermore, distributed learning rules are derived for Maximum Likelihood and Bayesian criteria under the assumption of fully observed time series in the training set.

关键词： Spiking neural network (SNN) exponential family model Maximum Likelihood Bayesian learning neuromorphic computing

来源：评论

学校读者我要写书评

暂无评论

distributed DNN Based User Association and Resource Optimization in mmWave networks

Distributed DNN Based User Association and Resource Optimiza...

引用

IEEE Global Communications conference (IEEE GLOBECOM)

作者： Zhang, Haisen Zhang, Haijun Wei Huangfu Liu, Wei Dong, Jiangbo Long, Keping Nallanathan, Arumugam Univ Sci & Technol Beijing Inst Artificial Intelligence Beijing Engn & Technol Res Ctr Convergence Networ Beijing Peoples R China China Mobile Grp Design Inst Co Ltd Beijing Peoples R China Queen Mary Univ London London England

ISBN: (纸本)9781728109626

Millimeter wave (mmWave) communication technology has become an attractive solution to meet exponential growth demand for mobile data services. In this paper, we propose a deep neural networks (DNN) based algorithm for user association and power optimization problem in mmWave hetero-geneous network on the basis of gradient iterative algorithm. We jointly design the user association and power optimization to maximize energy efficiency (EE) utilizing Lagrange dual decomposition and then approximate it by DNN models. In addition, an asynchronous distributed DNN based scheme is proposed, which divides the large network model into small distributed networks for distributed data processing on each small base station side to reduce computational time. Simulation results show that the proposed scheme can achieve a high EE with low computation time.

关键词： Deep neural networks

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301页 << < 134 135 136 137 138 139 140 141 142 143 > >>

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：