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

2,959 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,005 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,760 篇 工学
- 1,407 篇 计算机科学与技术...
- 684 篇 软件工程
- 490 篇 电气工程
- 397 篇 信息与通信工程
- 203 篇 控制科学与工程
- 130 篇 生物工程
- 79 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 59 篇 机械工程
- 54 篇 仪器科学与技术
- 49 篇 光学工程
- 34 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 材料科学与工程（可...
- 24 篇 安全科学与工程
- 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
517 篇 理学
- 226 篇 物理学
- 190 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
168 篇 artificial neura...
165 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
50 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
72 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 3005 条记录，以下是1211-1220 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 Normal Approach of Online Signature Using Stroke Point Warping - A Survey 3rd

A Normal Approach of Online Signature Using Stroke Point War...

引用

International conference on Computational Vision and Bio-Inspired Computing (ICCVBIC)

作者： Shyry, S. Prayla Srivanth, P. Thomson, Derrick Sathyabama Inst Sci & Technol Dept Comp Sci Engn Chennai Tamil Nadu India

ISBN: (纸本)9783030372187;9783030372170

In today's world, the method to identify the online verification technique is appeared with the help of the signature device. Some common human biometrics include iris recognition, retinal scanner, voice detection, fingerprint detector, and thumbprint detection. Fingerprint detector is used in the mobile devices. Traditionally, due to the in-built inconsistency of the collected signature, a normal procedure known as Stroke Point Warping (SPW) was recommended. In the proposed system, a normal methodology called DSUM (distributed Data Split up Model) for signature verification is used to improve the accuracy level of the extracted features. In this DSUM model, the signature area is being extracted and splitted into N number of blocks. For studying the features accurately each N blocks are being fetched up for multi modal feature extraction. The neural network (decision making) is being done by using the multiple scores and featured vectors. Nowadays, neural networks and deep learning gives good solution for problems in image identification, voice detection and natural language processing.

关键词： Biometrics distributed Data Split Up Model (DSUM) Inherent variability neural network Stroke Point Warping (SPW)

来源：评论

学校读者我要写书评

暂无评论

Unwrapping SAR interferograms with localized subsidence signal using deep neural network

Unwrapping SAR interferograms with localized subsidence sign...

引用

EUSAR 2021;13th European conference on Synthetic Aperture Radar

作者： Zhipeng Wu Teng Wang Robert Wang

Phase unwrapping is an indispensable processing step of InSAR. However, conventional methods often underestimate the deformation due to severe noise and/or dense fringes. Here, we develop a new deep neural network to unwrap interferograms with localized subsidence signal. We train the network using synthetic interferograms with two-dimensional Gaussian shape subsidence and complex Gaussian noises, and apply the network to real interferograms with localized mining subsidence. The proposed method outperforms the standard methods by 76.3% on synthetic interferograms and ~50-times faster on real interferograms. The promising result shows the potential for rapid monitoring and quantification local deformation distributed in large area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized neural Scene Representations

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quan...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Prabhudesai, Mihir Lal, Shamit Tung, Hsiao-Yu Fish Harley, Adam W. Potdar, Shubhankar Fragkiadaki, Katerina Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781728193601

Concept learning lies at the very heart of intelligence, providing organizing principles with which to comprehend the world (6). Most computer vision models learn concept classifiers or detectors using labelled examples of object boxes, poses and categories. Self-supervised or unsupervised approaches mostly focus on (pre)training CNNs on auxiliary pretext tasks to lessen the need for human labels for a downstream recognition task. The visual "concepts" learnt from pretext tasks are implicit and represented as distributed neural CNN activations (7). We see the following limitations with representing concepts (solely) as neural activations across multiple layers of a deep network: i) visual memory and computation are not separated (3), which means that computation increases exponentially with the number of visual concepts learnt, ii) concepts are not stored somewhere and cannot be referred to or retrieved on demand, iii) the number of concepts cannot increase automatically based on new visual experiences, rather it is determined by the processing architecture;this misaligns with the idea that animals are capable of spontaneous concept instantiation in novel scenes (2), iv) concepts cannot be mentally manipulated by imagining variations, transformations or mental simulations (8), v) concepts do not have any spatial dimension and are hard to use for spatial reasoning. © 2020 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

AccDP: Accelerated Data-Parallel distributed DNN Training for Modern GPU-Based HPC Clusters

AccDP: Accelerated Data-Parallel Distributed DNN Training fo...

引用

International conference on High Performance Computing

作者： Nawras Alnaasan Arpan Jain Aamir Shafi Hari Subramoni Dhabaleswar K Panda Department of Computer Science and Engineering The Ohio State University Columbus Ohio USA

Deep Learning (DL) has become a prominent machine learning technique due to the availability of efficient computational resources in the form of Graphics processing Units (GPUs), large-scale datasets and a variety of models. The newer generation of GPUs are being designed with special emphasis on optimizing performance for DL applications. Also, the availability of easy-to-use DL frameworks—like PyTorch and TensorFlow— has enhanced productivity of domain experts to work on their custom DL applications from diverse domains. However, existing Deep neural network (DNN) training approaches may not fully utilize the newly emerging powerful GPUs like the NVIDIA A100—this is the primary issue that we address in this paper. Our motivating analyses show that the GPU utilization on NVIDIA A100 can be as low as 43% using traditional DNN training approaches for small-to-medium DL models and input data size. This paper proposes AccDP—a data-parallel distributed DNN training approach—to accelerate GPU-based DL applications. AccDP exploits the Message Passing Interface (MPI) communication library coupled with the NVIDIA’s Multi-Process Service (MPS) to increase the amount of work assigned to parallel GPUs resulting in higher utilization of compute resources. We evaluate our proposed design on different small-to-medium DL models and input sizes on the state-of-the-art HPC clusters. By injecting more parallelism into DNN training using our approach, the evaluation shows up to 58% improvement in training performance on a single GPU and up to 62% on 16 GPUs compared to regular DNN training. Furthermore, we conduct an in-depth characterization to determine the impact of several DNN training factors and best practices—including the batch size and the number of data loading workers— to optimally utilize GPU devices. To the best of our knowledge, this is the first work that explores the use of MPS and MPI to maximize the utilization of GPUs in distributed DNN training.

关键词： Training Deep learning Productivity Performance evaluation Computational modeling Message passing neural networks

来源：评论

学校读者我要写书评

暂无评论

Survival Prediction Model of Renal Transplantation using Deep neural network 1

Survival Prediction Model of Renal Transplantation using Dee...

引用

1st IEEE International conference for Convergence in Engineering, ICCE 2020

作者： Chakraborty, Somenath Zhang, Chaoyang University of Southern Mississippi School of Computing Sciences and Computer Engineering Hattiesburg United States

ISBN: (纸本)9781728173405

The objectives of this paper are to explore ways to parallelize and distribute deep learning in multi-core and distributed settings. We have heuristically improved the training parameter setting by a Deep neural network (DNN) using quad-core CPU and Graphical processing Unit (GPU) and develop a setting to improve training performances. Along with that, a Parallel Phase neural network model (PHNNM) has been proposed for the prediction of the long-term survival of liver patients who undergo liver transplantation (LT). We made survival analysis of 13 years in the prediction of liver patients after LT and trained the liver transplantation system to follow up data of 13 years separately using a multilayer perceptron PHNNM model with proper selection of data attributes in conjunction with evaluating the survival probabilities of such data. This paper proved that our prediction model is suitable for the long-term prognosis of survival of patients after LT. The promising results are shown, in combination with the computational performances in terms of CPU and GPU. © 2020 IEEE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Parametric Versus Non-Parametric Text Classification Algorithms 15

A Comparative Study of Parametric Versus Non-Parametric Text...

引用

15th International conference on Development and Application Systems (DAS)

作者： Chistol, Mihaela Stefan Cel Mare Univ Suceava Suceava Romania

ISBN: (纸本)9781728168708

Evolution of modern technologies allowed to store the text in various digital formats such as e-mails, e-documents, libraries, etc. The amount of text data that is produced daily is increasing dramatically. Discovering useful patterns in text that can be represented in unstructured, semi-structured or structured format is a difficult task that requires a good understanding of machine learning algorithms. Finding a suitable algorithm for text mining tasks such as classification, clustering or natural language processing is a demanding situation that tests researchers' abilities. This paper provides an overview of the text mining process also, presents a comparison of the performance and limitations of two predictive models generated using the parametric Naive Bayes algorithm and non-parametric Deep Learning neural network. RapidMiner data science software platform has been used for models' implementations and e-mail classification.

关键词： text classification text mining machine learning Naive Bayes neural network performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification of Odor Using Attention Based neural network 16th

Feature Extraction and Classification of Odor Using Attentio...

引用

16th International Symposium on distributed Computing and Artificial Intelligence (DCAI)

作者： Fukuyama, Kohei Matsui, Kenji Omatsu, Sigeru Rivas, Alberto Manuel Corchado, Juan Osaka Inst Technol Fac Robot & Design Osaka Japan Univ Salamanca BISITE Digital Innovat Hub Salamanca Spain

ISBN: (纸本)9783030238872;9783030238865

In this paper, we explored a new approach of odor identification using deep learning. We also verified whether it is possible to classify odors in real time. Attention recurrent neural network (ARNN) is mainly used in the sequence to sequence model in terms of natural language processing field. We applied the simple ARNN embedding part with auto encoder to the deep learning model. This model can visualize the attention part of input data. Six types of aroma oil were measured using five types of metal oxide semiconductor gas sensors. Using the measured data, the accuracy was 96.83 [%] for training data and 96.88 [%] for the verification data.

关键词： Deep learning Sequence to sequence Attention mechanism Odor classification Visualization Metal oxide gas sensor

来源：评论

学校读者我要写书评

暂无评论

Understanding the Resource Demand Differences of Deep neural network Training 19th

Understanding the Resource Demand Differences of Deep Neural...

引用

19th International conference on Algorithms and Architectures for Parallel processing (ICA3PP)

作者： Du, Jiangsu Zhu, Xin Hu, Nan Du, Yunfei Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9783030389611;9783030389604

More deep neural networks (DNN) are deployed in the real world, while the heavy computing demand becomes an obstacle. In this paper, we analyze the resource demand differences of DNN training and help understand its performance characteristic. In detail, we study both shared-memory and message-passing behavior in distributed DNN training from layer-level and model-level perspectives. From layer-level perspective, we evaluate and compare basic layers' resource demand. From model-level perspective, we measure parallel training of representative models then explain the causes of performance differences based on their structures. Experimental results reveal that different models vary in resource demand and even a model can have very different resource demand with different input sizes. Further, we give out some observations and recommendations on performance improvement of on-chip training and parallel training.

关键词： Deep neural network training Performance Resource demand differences

来源：评论

学校读者我要写书评

暂无评论

An Airfoil Mesh Quality Criterion using Deep neural networks 12

An Airfoil Mesh Quality Criterion using Deep Neural Networks

引用

12th International conference on Advanced Computational Intelligence (ICACI)

作者： Chen, Xinhai Liu, Jie Gong, Chunye Pang, Yufei Chen, Bo Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China China Aerodynam Res & Dev Ctr Mianyang Sichuan Peoples R China

ISBN: (数字)9781728142487

ISBN: (纸本)9781728142487

The quality of the mesh is one of the most critical aspects for solving partial differential equations (PDEs) in applications of Computational Fluid Dynamics. Many geometry criteria have been proposed and are widely used in business pre-processing software like ICEM CFD, PointWise, Gambit. However, these traditional geometry criteria fail to recognize some quality features that seriously affect the accuracy of numerical calculations, such as density and distribution of mesh elements. These quality features are usually evaluated based on engineering experience, which heavily increases the pre-processing cost and requires extensive engineering experience. In this paper, we introduce a deep learning model to solve the mentioned issues by offline learning. The proposed model is small and fast and can be embedded in pre-processing software. Experiment results show that the derived model is capable of performing the quality evaluating task and achieve an accuracy of 93.8%.

关键词： deep neural network mesh quality pre-processing software computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

PC-BNA: Parallel Convolution Binary neural network Accelerator

PC-BNA: Parallel Convolution Binary Neural Network Accelerat...

引用

IEEE International conference on High Performance Computing and Communications (HPCC)

作者： Haihui Liu Yuang Zhang Xiangwei Zheng Mengxin Yu Baoxu An Xiaojie Liu Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology School of Information Science and Engineering Shandong Normal University Jinan China

Binary neural network (BNN) is widely used in speech recognition, image processing and other fields to save memory and speed up computing. However, the accuracy of the existing binarization scheme in the realistic dataset is obviously low, and the input layer uses 32-bit floating point to avoid excessive precision loss, which requires additional computing units and increases the computational burden. Therefore, it is very important to improve the input layer, save computing resources and reduce precision loss. In this paper, we propose a parallel convolution binary neural network accelerator architecture (PC-BNA). Based on our proposed BNN model, we design an efficient field programmable gate array (FPGA) based accelerator. The input of the first layer is binarized, the traditional binary convolution layer is replaced by a parallel binary convolution, and the network building blocks are improved. The experimental results show that the proposed PC-BNA has higher accuracy and better performance on CIFAR-10. The image recognition accuracy is as high as 91.4%, which is superior to the state-of-art of the BNN accelerator. Compared to the state-of-the-art BNN model, when using the same model size, the use of look-up-table (LUT) saves 9.08%, and the digital signal processor (DSP) saves 27.7%. The results suggest that it is promising for PC-BNA in future high performance mobile artificial intelligence applications.

关键词： Performance evaluation Convolution neural networks Digital signal processors Speech recognition Logic gates Mobile handsets

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 << < 118 119 120 121 122 123 124 125 126 127 > >>

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：