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

4,706 篇 会议
641 篇 期刊文献
3 篇 学位论文

馆藏范围

5,350 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,487 篇 工学
- 823 篇 电气工程
- 765 篇 计算机科学与技术...
- 319 篇 信息与通信工程
- 238 篇 控制科学与工程
- 159 篇 软件工程
- 126 篇 机械工程
- 94 篇 仪器科学与技术
- 40 篇 电子科学与技术（可...
- 31 篇 交通运输工程
- 15 篇 航空宇航科学与技...
- 11 篇 测绘科学与技术
- 11 篇 生物医学工程（可授...
- 10 篇 土木工程
- 9 篇 网络空间安全
- 7 篇 材料科学与工程（可...
- 4 篇 动力工程及工程热...
- 4 篇 矿业工程
- 4 篇 石油与天然气工程
- 4 篇 核科学与技术
161 篇 理学
- 68 篇 系统科学
- 54 篇 数学
- 19 篇 生物学
- 17 篇 物理学
- 9 篇 统计学（可授理学、...
- 5 篇 地球物理学
- 4 篇 地理学
100 篇 管理学
- 98 篇 管理科学与工程(可...
49 篇 医学
- 45 篇 临床医学
38 篇 文学
- 37 篇 新闻传播学
7 篇 艺术学
- 7 篇 设计学（可授艺术学...
6 篇 农学
2 篇 教育学
1 篇 军事学

主题

5,350 篇 inference algori...
534 篇 computational mo...
409 篇 fuzzy systems
402 篇 algorithm design...
386 篇 fuzzy logic
382 篇 bayesian methods
370 篇 computer science
334 篇 training
330 篇 neural networks
302 篇 approximation al...
292 篇 bayes methods
229 篇 optimization
225 篇 clustering algor...
217 篇 signal processin...
211 篇 data mining
207 篇 fuzzy sets
203 篇 heuristic algori...
193 篇 prediction algor...
192 篇 accuracy
185 篇 feature extracti...

机构

15 篇 school of electr...
11 篇 university of ch...
10 篇 school of comput...
10 篇 zhejiang univ co...
9 篇 tsinghua univers...
9 篇 purple mt labs p...
9 篇 national univers...
8 篇 microsoft resear...
8 篇 university of mi...
7 篇 department of co...
7 篇 tianjin univ col...
7 篇 department of el...
7 篇 university of so...
7 篇 department of au...
7 篇 tsinghua univ de...
6 篇 ibm thomas j. wa...
6 篇 nanyang technol ...
6 篇 university of so...
6 篇 department of el...
6 篇 department of co...

作者

8 篇 pushmeet kohli
7 篇 li cheng
7 篇 edward r. doughe...
7 篇 wei li
7 篇 xiaodong wang
7 篇 t.s. huang
7 篇 erik b. sudderth
7 篇 a. taylan cemgil
7 篇 p. baranyi
7 篇 nizar bouguila
6 篇 simon godsill
6 篇 alan s. willsky
6 篇 hui wang
6 篇 ying wu
6 篇 wang wei
6 篇 s. suresh
6 篇 chen yongxin
6 篇 yang xu
6 篇 luca benini
6 篇 viktor k. prasan...

语言

5,287 篇 英文
51 篇 其他
11 篇 中文
1 篇 西班牙文

检索条件"主题词=Inference algorithms"

共 5350 条记录，以下是131-140 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：

RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis

RayGauss: Volumetric Gaussian-Based Ray Casting for Photorea...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Hugo Blanc Jean-Emmanuel Deschaud Alexis Paljic Centre for Robotics Mines Paris - PSL PSL University Paris France

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Differentiable volumetric rendering-based methods made significant progress in novel view synthesis. On one hand, innovative methods have replaced the Neural Radiance Fields (NeRF) network with locally parame-terized structures, enabling high-quality renderings in a reasonable time. On the other hand, approaches have used differentiable splatting instead of NeRF's ray casting to optimize radiance fields rapidly using Gaussian kernels, allowing for fine adaptation to the scene. However, differentiable ray casting of irregularly spaced kernels has been scarcely explored, while splatting, despite enabling fast rendering times, is susceptible to clearly visible artifacts. Our work closes this gap by providing a physically consistent formulation of the emitted radiance c and density σ, decomposed with Gaussian functions associated with Spherical Gaussians/Harmonics for all-frequency colorimetric representation. We also introduce a method enabling differentiable ray casting of irregularly distributed Gaussians using an algorithm that integrates radiance fields slab by slab and leverages a BVH structure. This allows our approach to finely adapt to the scene while avoiding splatting artifacts. As a result, we achieve superior rendering quality compared to the state-of-the-art while maintaining reasonable training times and achieving inference speeds of 25 FPS on the Blender dataset. Project page with videos and code: ***

关键词： Training Hands Casting Computer vision Rendering (computer graphics) Neural radiance field inference algorithms Slabs Kernel Videos

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Diabetes Mellitus Based on Artificial Intelligence algorithms

Diagnosis of Diabetes Mellitus Based on Artificial Intellige...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Akbar Rashidov Dilmurod Mardonov Akbar Soliev Department of Artificial intelligence and Information systems Samarkand state university Samarkand Uzbekistan Department of Scientific affairs and innovations Urgut branch of Samarkand state university Urgut Uzbekistan

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

It is known that artificial intelligence algorithms provide inference capabilities about new objects based on the analysis of an existing dataset. This feature of artificial intelligence makes it possible to use it as a solution in many issues. One such problem is the issue of diagnosing diabetes mellitus, which is considered one of the most common diseases in medicine. This research work is devoted to the solution of this issue, the study highlights the process of diagnosing diabetes mellitus based on classification algorithms. In the study, the data set is selected first and this data set is passed through the data profling and data cleaning stages. Based on the compiled data set, the artificial intelligence algorithms Logistic regression, Support Vector Machines (SVM), Random Forest, and Nearest Neighbors are taught and tested. In order to increase the accuracy of the results of the study, the hyper parameters of the selected artificial intelligence model are adjusted. The results obtained after the study are analyzed and the research conclusion is made.

关键词： Support vector machines Logistic regression Accuracy Cleaning inference algorithms Diabetes Classification algorithms Artificial intelligence Random forests Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition

Breaking Through the Spike: Spike Window Decoding for Accele...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Zhang Tian-Hao Zhang Chao Luo Hui Zhou Chao Yang Xinyuan Qian Xu-Cheng Yin *** GROUP Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia. To optimize system performance in specific scenarios, the Weighted Finite-State Transducer (WFST) is extensively used to integrate acoustic and language models, leveraging its capacity to implicitly fuse language models within static graphs, thereby ensuring robust recognition while also facilitating rapid error correction. However, WFST necessitates a frame-by-frame search of CTC posterior probabilities through autoregression, which significantly hampers inference speed. In this work, we thoroughly investigate the spike property of CTC outputs and further propose the conjecture that adjacent frames to non-blank spikes carry semantic information beneficial to the model. Building on this, we propose the Spike Window Decoding algorithm, which greatly improves the inference speed by making the number of frames decoded in WFST linearly related to the number of spiking frames in the CTC output, while guaranteeing the recognition performance. Our method achieves SOTA recognition accuracy with significantly accelerates decoding speed, proven across both AISHELL-1 and large-scale In-House datasets, establishing a pioneering approach for integrating CTC output with WFST.

关键词： Accuracy Semantics Buildings Signal processing algorithms inference algorithms Acoustics Decoding Windows Speech processing Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of State-of-the-Art Object Detection algorithms for Autonomous Vehicles in DonkeyCar Simulator

A Comparative Study of State-of-the-Art Object Detection Alg...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Naoby Prawira Nungki Selviandro Gia Septiana Wulandari School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

In recent years, autonomous vehicle technology has become a major area of focus within the automotive industry. Nevertheless, the advancement of object detection methodologies in autonomous vehicles remains limited, particularly with regard to the latest object detection methodologies. In the development of object detection capabilities for autonomous vehicles, it is important to utilize simulation scenarios that are safe for the surrounding environment. The objective of this research is to evaluate the efficacy of object detection algorithms in a simulation environment utilizing the DonkeyCar platform. The efficacy of several state-of-the-art algorithms will be evaluated based on two metrics: general performance measurements and scenario tests on the DonkeyCar simulator. This research compares several variants of three state-of-the-art algorithms, namely faster R-CNN, YOLO, and SSD, to determine the most efficient algorithm for real-time object detection in the context of autonomous vehicles. The study demonstrates that YOLOv10-N exhibits superior performance, achieving an mAP@0.50 value of 0.940 and maintaining an inference time of 35 FPS.

关键词： YOLO Performance evaluation Accuracy Computational modeling Scalability Object detection Real-time systems inference algorithms Object recognition Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Detection Algorithm for Distribution Network Insulators Based on YOLOv8n-EdgePro

A Detection Algorithm for Distribution Network Insulators Ba...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Jiming Tian Yunong Tian Binru Liu Yanrong Liu Zize Liang CAS Engineering Laboratory for Intelligent Industrial Vision Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation North China Electric Power University Baoding China College of Electrical Engineering Xinjiang industry technical college Urumqi China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

The detection of insulators in power distribution networks plays a vital role in ensuring the overall safety and stability of the power system. Insulators serve as essential components in maintaining the integrity of power transmission by preventing electrical faults. As distribution networks expand and become more complex, efficient and accurate detection methods are required to prevent potential failures and ensure system reliability. Traditional manual inspection methods are labor-intensive and prone to errors, making automated detection an essential solution. This paper introduces YOLOv8n-EdgePro, a lightweight yet effective object detection algorithm tailored for insulator detection. By incorporating advanced techniques such as depthwise separable convolutions and attention mechanisms, the algorithm significantly enhances feature extraction, especially for small and hard-to-detect insulators in challenging environments. Additionally, the lightweight design reduces computational complexity, enabling deployment on edge devices such as drones or portable inspection units. The algorithm strikes an optimal balance between detection accuracy and efficiency, addressing the dual needs for high performance and fast inference speeds, essential for real-time applications in large-scale distribution networks. Through this approach, the paper aims to provide a reliable, scalable solution for automating insulator detection and monitoring, contributing to the development of smarter and more resilient power grids.

关键词： Accuracy Computational modeling Distribution networks Object detection Power system stability Inspection Insulators Feature extraction inference algorithms Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Membership Function Shape Optimization of Fuzzy PIDN Controller Based on CTO to Track Output Power of PWR System

Membership Function Shape Optimization of Fuzzy PIDN Control...

引用

Industrial Electronics: Developments & Applications (ICIDeA), IEEE International Conference on-

作者： Sulakshan Naha Dushmanta Kumar Das Department of EEE NIT Nagaland Dimapur Nagaland India

ISBN: (数字)9798331533205

ISBN: (纸本)9798331533212

The shape of fuzzy membership function (MF) is important for performance analysis of any fuzzy inference system (FIS). Normally MFs are chosen by engineering knowledge and expertise but this may not reflect optimal performance in control problems. The aim of the paper is to present a method by using class topper optimization (CTO) algorithm to optimize the shape of membership function of FIS for PWR system. The method is basically to choose the correct membership function for the fuzzy PIDN controller to track output power of PWR system. The simulation result reflects good tracking performance in the proposed work.

关键词： Knowledge engineering Fuzzy logic Shape Simulation inference algorithms Performance analysis Power generation Optimization

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Unsupervised Audio-visual Speech Enhancement

Diffusion-based Unsupervised Audio-visual Speech Enhancement

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jean-Eudes Ayilo Mostafa Sadeghi Romain Serizel Xavier Alameda-Pineda CNRS Inria Loria Université de Lorraine Nancy France Inria Université Grenoble Alpes Grenoble France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper proposes a new unsupervised audiovisual speech enhancement (AVSE) approach that combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. First, the diffusion model is pre-trained on clean speech conditioned on corresponding video data to simulate the speech generative distribution. This pre-trained model is then paired with the NMF-based noise model to estimate clean speech iteratively. Specifically, a diffusion-based posterior sampling approach is implemented within the reverse diffusion process, where after each iteration, a speech estimate is obtained and used to update the noise parameters. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervised-generative AVSE method. Additionally, the new inference algorithm offers a better balance between inference speed and performance compared to the previous diffusion-based method. Code and demo available at: https://***/fast_UdiffSE

关键词： Visualization Runtime Speech coding Lips Noise Signal processing algorithms Speech enhancement Diffusion models inference algorithms Iterative methods

来源：评论

学校读者我要写书评

暂无评论

StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models

StableQuant: Layer Adaptive Post-Training Quantization for S...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yeona Hong Hyewon Han Woo-Jin Chung Hong-Goo Kang Department of Electrical and Electronic Engineering Yonsei University Seoul Republic of Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully employed for compressing large language models (LLMs) due to its ability to bypass additional fine-tuning, directly applying these techniques to SFMs may not yield optimal results, as SFMs utilize distinct network architecture for feature extraction. StableQuant demonstrates optimal quantization performance regardless of the network architecture type, as it adaptively determines the quantization range for each layer by analyzing both the scale distributions and overall performance. We evaluate our algorithm on two SFMs, HuBERT and wav2vec2.0, for an automatic speech recognition (ASR) task, and achieve superior performance compared to traditional PTQ methods. StableQuant successfully reduces the sizes of SFM models to a quarter and doubles the inference speed while limiting the word error rate (WER) performance drop to less than 0.3% with 8-bit quantization.

关键词： Adaptation models Quantization (signal) Limiting Foundation models Large language models Signal processing algorithms Network architecture inference algorithms Speech processing Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Learned ReLU-Based Soft Thresholding: A Data-Driven Method for Non-Negative Sparse Signal Recovery

Learned ReLU-Based Soft Thresholding: A Data-Driven Method f...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Akash Sen Pradyumna Pradhan Ramunaidu Randhi C. S. Sastry Department of Mathematics Indian Institute of Technology Hyderabad India Department of Humanities and Sciences Indian Institute of Petroleum and Energy Visakhapatnam India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Linear Inverse Problems (LIPs) with non-negative sparse constraints on the target signal are critical in numerous applications across various fields. Among the recently proposed methods dealing with LIPs, model-based deep learning methods, particularly deep unrolling, have gained popularity due to their interpretability, efficiency, and superior performance compared to traditional iterative methods. In this work, we propose a model-driven deep learning method by unrolling the recently developed ReLU-based Hard Thresholding (RHT) algorithm for non-negative sparse signal recovery. Specifically, we employ soft thresholding activation instead of hard thresholding in the unrolling of RHT, which enhances the model performance during backpropagation. The primary advantages of the proposed Learned ReLU-based Soft Thresholding (LRST) include interpretability and faster inference after the network is trained. Our numerical experiments demonstrate that the proposed LRST outperforms its classical counterparts, showcasing its potential for more effective non-negative sparse signal recovery.

关键词： Deep learning Inverse problems Lips Signal processing algorithms Signal processing Network architecture inference algorithms Numerical models Iterative methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

EE4: The Next Decade of AI – Barriers, Opportunities, & Directions

EE4: The Next Decade of AI – Barriers, Opportunities, & Dir...

引用

IEEE International Conference on Solid-State Circuits (ISSCC)

EE4: The Next Decade of AI – Barriers, Opportunities, & Directions.

ISBN: (数字)9798331541019

ISBN: (纸本)9798331541026

EE4: The Next Decade of AI – Barriers, Opportunities, & Directions.

关键词： Artificial intelligence Computational modeling Technological innovation Silicon Data centers Solid state circuits Smart phones Sensors Regulation inference algorithms

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 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：