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

10,058 篇 会议
276 篇 期刊文献
36 册 图书
2 篇 科技报告

馆藏范围

10,372 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,280 篇 工学
- 5,756 篇 计算机科学与技术...
- 3,610 篇 软件工程
- 1,367 篇 信息与通信工程
- 1,287 篇 电气工程
- 909 篇 控制科学与工程
- 831 篇 电子科学与技术（可...
- 465 篇 机械工程
- 462 篇 生物工程
- 387 篇 光学工程
- 370 篇 动力工程及工程热...
- 364 篇 生物医学工程（可授...
- 290 篇 仪器科学与技术
- 261 篇 化学工程与技术
- 239 篇 交通运输工程
- 232 篇 网络空间安全
- 205 篇 材料科学与工程（可...
- 187 篇 土木工程
- 184 篇 安全科学与工程
- 183 篇 建筑学
2,754 篇 理学
- 1,405 篇 数学
- 872 篇 物理学
- 503 篇 生物学
- 358 篇 统计学（可授理学、...
- 345 篇 化学
- 240 篇 系统科学
1,334 篇 管理学
- 820 篇 管理科学与工程(可...
- 630 篇 图书情报与档案管...
- 365 篇 工商管理
445 篇 医学
- 346 篇 临床医学
- 192 篇 基础医学(可授医学...
184 篇 教育学
141 篇 法学
124 篇 经济学
48 篇 农学
41 篇 军事学
31 篇 文学
10 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

1,025 篇 program processo...
727 篇 computer archite...
418 篇 computational mo...
384 篇 hardware
343 篇 high performance...
260 篇 parallel process...
238 篇 computer science
192 篇 optimization
171 篇 benchmark testin...
164 篇 concurrent compu...
163 篇 application soft...
159 篇 runtime
156 篇 computer vision
149 篇 bandwidth
129 篇 registers
129 篇 libraries
129 篇 deep learning
122 篇 parallel program...
120 篇 scalability
120 篇 throughput

机构

69 篇 college of compu...
57 篇 school of comput...
55 篇 university of ch...
44 篇 school of comput...
33 篇 department of co...
32 篇 college of compu...
31 篇 univ chinese aca...
30 篇 school of comput...
30 篇 tsinghua univers...
27 篇 school of comput...
25 篇 school of data a...
23 篇 college of compu...
23 篇 computer network...
23 篇 high energy astr...
22 篇 graduate school ...
21 篇 graduate school ...
21 篇 college of compu...
20 篇 center for astro...
20 篇 department of ph...
20 篇 department of ph...

作者

25 篇 tokuno h.
24 篇 ikeda d.
23 篇 belz j.w.
22 篇 jui c.c.h.
22 篇 oshima a.
22 篇 tsuda r.
22 篇 kim j.h.
22 篇 bergman d.r.
22 篇 allen m.
22 篇 matsuyama t.
22 篇 wong t.
22 篇 ishii t.
22 篇 kim s.w.
22 篇 takamura m.
22 篇 yashiro k.
22 篇 kadota k.
22 篇 mayta r.
22 篇 ozawa s.
22 篇 kasami s.
22 篇 rodriguez d.c.

语言

9,909 篇 英文
422 篇 其他
53 篇 中文
3 篇 西班牙文
2 篇 土耳其文
1 篇 葡萄牙文

检索条件"任意字段=Conference on High Performance Computer Modernization Program"

共 10372 条记录，以下是551-560 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：

Short Paper: Accelerating Hyperparameter Optimization Algorithms with Mixed Precision

Short Paper: Accelerating Hyperparameter Optimization Algori...

引用

2023 International conference on high performance Computing, Network, Storage, and Analysis, SC Workshops 2023

作者： Aach, Marcel Sarma, Rakesh Inanc, Eray Riedel, Morris Lintermann, Andreas Jülich Supercomputing Centre Jülich Germany University of Iceland Reykjavík Iceland

ISBN: (纸本)9798400707858

Hyperparameter Optimization (HPO) of Neural Networks (NNs) is a computationally expensive procedure. On accelerators, such as NVIDIA Graphics Processing Units (GPUs) equipped with Tensor Cores, it is possible to speed-up the NN training by reducing the precision of some of the NN parameters, also referred to as mixed precision training. This paper investigates the performance of three popular HPO algorithms in terms of the achieved speed-up and model accuracy, utilizing early stopping, Bayesian, and genetic optimization approaches, in combination with mixed precision functionalities. The benchmarks are performed on 64 GPUs in parallel on three datasets: two from the vision and one from the Computational Fluid Dynamics domain. The results show that larger speed-ups can be achieved for mixed compared to full precision HPO if the checkpoint frequency is kept low. In addition to the reduced runtime, small gains in generalization performance on the test set are observed. © 2023 ACM.

关键词： program processors

来源：评论

学校读者我要写书评

暂无评论

Explaining Convolutional Neural Networks for EEG-based Brain-computer Interface Using Influence Functions

Explaining Convolutional Neural Networks for EEG-based Brain...

引用

2023 IEEE International conference on Systems, Man, and Cybernetics, SMC 2023

作者： Park, Hoonseok Park, Donghyun Kim, Sangyeon Choo, Sanghyun Nam, Chang. S. Lee, Sangwon Jung, Jae-Yoon Kyung Hee University Department of Big Data Analytics Korea Republic of North Carolina State University Fitts Department of Industrial and Systems Engineering United States School of Industrial and Management Engineering Korea University Korea Republic of

ISBN: (纸本)9798350337020

Although the high performance of the convolutional neural networks (CNNs) for brain-computer interface (BCI) tasks based on raw electroencephalography (EEG) signals, the explanation of the prediction result remains challenging owing to their complex structure and numerous parameters. We propose a novel framework for explaining CNNs for EEG-based BCI tasks by using the perturbation-based influence scores. The method supports the interpretation of CNN classification for EEG signals at both the example-level and the feature-level. The experiments on the BCIC III-IVa dataset demonstrate that the proposed method is effective for not only the interpretation of the predictive models, but also for the improvement of the classification accuracy. © 2023 IEEE.

关键词： Brain-computer interface (BCI) Electroencephalography (EEG) Influence scores Input perturbations Machine learning interpretation Motor imagery classification

来源：评论

学校读者我要写书评

暂无评论

Research on Community Discovery Techniques Based on Knowledge Distillation 20

Research on Community Discovery Techniques Based on Knowledg...

引用

20th International computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Hong, Tang Zhen, Liu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798350318982

Graph Neural Networks (GNN) have found broad applications in diverse domains, including community detection, classification of nodes, and prediction of links. Unfortunately, in the real world, many networks usually have the problem of insufficient connection and label information, and GNN mainly relies on graph-based feature propagation and smoothing operations for graph task analysis. In the absence of connection and label information, the feature propagation operation of GNN will be greatly affected., so these problems pose an obstacle to the performance of GNN. In this context, we introduce an innovative model for community discovery based on knowledge distillation. The objective is to extract information on community structures from intricate networks and apply it to a student model, thus improving the effectiveness of community detection tasks. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Robust Lane Detection via Expanded Self Attention 22

Robust Lane Detection via Expanded Self Attention

引用

22nd IEEE/CVF Winter conference on Applications of computer Vision (WACV)

作者： Lee, Minhyeok Lee, Junhyeop Lee, Dogyoon Kim, Woojin Hwang, Sangwon Lee, Sangyoun Yonsei Univ Sch Elect & Elect Engn Seoul South Korea

ISBN: (纸本)9781665409155

The image-based lane detection algorithm is one of the key technologies in autonomous vehicles. Modern deep learning methods achieve high performance in lane detection, but it is still difficult to accurately detect lanes in challenging situations such as congested roads and extreme lighting conditions. To be robust on these challenging situations, it is important to extract global contextual information even from limited visual cues. In this paper, we propose a simple but powerful self-attention mechanism optimized for lane detection called the Expanded Self Attention (ESA) module. Inspired by the simple geometric structure of lanes, the proposed method predicts the confidence of a lane along the vertical and horizontal directions in an image. The prediction of the confidence enables estimating occluded locations by extracting global contextual information. ESA module can be easily implemented and applied to any encoder-decoder-based model without increasing the inference time. The performance of our method is evaluated on three popular lane detection benchmarks (TuSimple, CULane and BDD100K). We achieve state-of-the-art performance in CULane and BDD100K and distinct improvement on TuSimple dataset. The experimental results show that our approach is robust to occlusion and extreme lighting conditions.

关键词： Deep learning Visualization computer vision Lane detection Roads Lighting Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Driven Multi-Level Dynamical Fusion for Single-Cell Multi-Omics Cell Type Annotation

Multi-Task Driven Multi-Level Dynamical Fusion for Single-Ce...

引用

2024 IEEE International conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Jiawei Chen, Shizhan Han, Zongbo Li, Wei Tang, Jijun Guo, Fei Tianjin University College of Intelligence and Computing Tianjin300072 China Nankai University College of Artificial Intelligence Tianjin518055 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Central South University School of Computer Science and Engineering Changsha410083 China

ISBN: (纸本)9798350386226

The emergence of single-cell multi-omics sequencing technology has enabled the simultaneous profiling of diverse omics data within individual cells. It offers a more comprehensive perspective on cellular phenotypes and heterogeneity. However, single-cell multi-omics data are inherently high-dimensional and heterogeneous. Due to technical limitations and scarce starting materials, the data are often affected by noise and dropout effects. To address these challenges, we propose a novel multitask driven multi-level dynamical fusion algorithm for single-cell multi-omics cell type annotation, named scMMDyn. Our approach incorporates reconstruction and classification auxiliary tasks to guide the training of trustworthy modules at both the feature and modality levels. It executes dynamical fusion during these stages and finally achieves cross-modality fusion via an attention mechanism. This method effectively mitigates data quality issues through reconstruction tasks and feature-level dynamical fusion while providing interpretability at both feature and modality levels. Experimental results across diverse single-cell multi-omics datasets show that our method surpasses existing approaches in cell type annotation. © 2024 IEEE.

关键词： cell type annotation multi-task mutli-level dynamical fusion single-cell multi-omics trustworthy

来源：评论

学校读者我要写书评

暂无评论

Self-aligned top-gate amorphous ITZO TFTs with high-k AlOx insulator with Oxygen-plasma formed source/drain

Self-aligned top-gate amorphous ITZO TFTs with high-k AlOx i...

引用

International conference on Display Technology, 2024

作者： Jiang, Wei Wong, Man Department of Electronic and Computer Engineering Kowloon Hong Kong The State Key Laboratory on Advanced Displays and Optoelectronics Technologies The Hong Kong University of Science and Technology Kowloon Hong Kong Guangzhou HKUST Fok Ying Tung Graduate School Guangzhou511458 China

This work develops self-aligned top-gate (SA-TG) amorphous indium-tin-zinc oxide (ITZO) thin-film transistors (TFT) with high-k AlOx gate insulator based on oxygen-plasma formed source/drain technique. The fabricated SA-TG TFTs based on this technique demonstrate good electrical performance, such as source/drain resistivity of less than 0.005Ω cm, high field-effect mobility of 35.2 cm2/Vs, and near-zero turn-on voltage. Additionally, the SA-TG high-k devices exhibiting short-channel effects only when the channel length is scaled to ~0.8 μm and demonstrated strong stability when subjected to thermal and gate bias stress. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

***: Julia programming Language Application for Molecular Dynamics Trajectory Processing 9th

***: Julia Programming Language Application for Molecular D...

引用

9th Russian Supercomputing Days International conference, RuSCDays 2023

作者： Pisarev, Vasily Panov, Mikhail HSE University Moscow Russia Joint Institute for High Temperatures of RAS Moscow Russia

ISBN: (纸本)9783031494345

Molecular simulations and molecular dynamics in particular are among the most performance-demanding computational methods. As the scale of simulations increases, the task of processing the simulation results becomes a computationally-hungry problem as well. The usual approach to build easy-to-use post-processing tools is based on providing an interface to a high-performance library called from a scripting language such as Python. We overview the advantages of using Julia programming language for building such tools, due to its easy surface syntax close to that of scripting languages and JIT compilation enabling high runtime performance. Then, we overview the package *** written in Julia, regarding its customizability, abstractions for common processing workflows and performance characteristics. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

computer Aided Art Design System Based on B/S Structure

Computer Aided Art Design System Based on B/S Structure

引用

2023 International conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Yi, Caixue Li, Ying School of Artificial Intelligence Chongqing Three Gorges Vocational College Wanzhou Chongqing China Infrastructure Logistics Division Chongqing Three Gorges Vocational College Wanzhou Chongqing China

ISBN: (纸本)9798350315455

In response to the shortcomings of traditional C/S architecture in system performance, compatibility, and other aspects, the author proposes a computer-aided art design system based on B/S architecture. The system adopts a three-layer framework structure, and the hardware part includes a visual interaction subsystem, a graphics processing module, a control module, and an execution module, the author elaborated on the functions of each module separately;At the software level, the system designs the main control process and compilation rules based on JSP technology, and executes the saywhat instruction set program;The database design is based on the SQL Server language and is connected to hardware modules in an embedded manner. The system test results show that the computer assisted system based on B/S architecture has stable functions, faster system response under high load conditions, and stronger scalability. © 2023 IEEE.

关键词： Art design system B/S structure JSP technology SQL Server Language Three story frame structure

来源：评论

学校读者我要写书评

暂无评论

Loradrop: An Efficiency Optimization Method for Lora 7

Loradrop: An Efficiency Optimization Method for Lora

引用

7th International conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Chen, Zhongshuo Liu, Huiyi Wei, Xianglong School of Computer and Information Hohai University Nanjing China

ISBN: (纸本)9798350382877

The computational cost of large-scale pre-trained models based on Transformer is prohibitively high, with demanding training requirements that are often beyond the capabilities of consumer-grade GPUs for fine-tuning on downstream tasks. Recently, the widely adopted fine-tuning method, LoRA, addresses these drawbacks by decomposing and replacing matrices within the model, along with freezing a significant portion of model parameters to reduce the number of trainable parameters. In this paper, we propose the LoRADrop method, which further reduces the number of LoRA modules in lower Transformer layers based on the LoRA approach, aiming to decrease the training cost of model fine-tuning. We conducted comparative experiments on eight tasks from the GLUE benchmark, including full-model fine-tuning, LoRA fine-tuning, and LoRADrop fine-tuning methods. Our results demonstrate that the LoRADrop method significantly accelerates training speed (speed improvement ranging from 12% to 40%) while achieving comparable or even superior task performance compared to the LoRA method in multiple downstream tasks. © 2023 IEEE.

关键词： program processors

来源：评论

学校读者我要写书评

暂无评论

An Approach to Analyze the Permanent Magnet Motor Torque Ripple for Improving Torque Power Curves used in Electric Vehicles 15

An Approach to Analyze the Permanent Magnet Motor Torque Rip...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Neelakandan, Varatharaj Prabakaran, B. Balaji, D. Suresh, P. Maheswaran, S. Indhumathi, N. Hindustan Institute of Technology and Science Chennai India Vellore Institute of Technology School of Computer Science and Engineering TamilNadu Vellore India Kongu Engineering College Department of Electronics and Communication Engineering TamilNadu Erode India

ISBN: (纸本)9798350370249

An electric car's permanent magnet synchronous motor (PMSM) will be designed and evaluated for performance in this research article. In order to satisfy the unique needs of the electric car and improve its overall performance, the goal is to achieve the highest torque density and the lowest torque ripple. The study's goal is to increase the electric vehicle's power density to do this, which calls for the use of a high-power-density motor. This is addressed by conducting an optimization procedure to increase the generated torque while making sure that the chosen motor stays within the defined size and volume restrictions. The efficient use of permanent magnet (PM) materials with strong thermal limiting capacity, which can enhance the power, is a critical component of this improvement. The efficient use of permanent magnet (PM) materials with high thermal limiting capacity, which may boost the power output under both peak and continuous loads, is a vital component of this optimization. The most important motor design parameters are carefully chosen throughout the optimization process to have the greatest influence on motor performance. Using the finite element software program 'CAE Software,' the research team tests and executes the suggested motor design. The overall goal of this project is to build a PMSM that is highly effective and adapted to the needs of electric vehicles. The goal of the study is to optimize critical motor parameters and use modern PM materials with higher thermal properties in order to increase torque density and reduce torque ripple of the motor. © 2024 IEEE.

关键词： Permanent magnets

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500页 << < 52 53 54 55 56 57 58 59 60 61 > >>

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：