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

61 篇 会议

馆藏范围

61 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

59 篇 工学
- 59 篇 计算机科学与技术...
- 57 篇 电气工程
- 2 篇 软件工程
- 1 篇 生物工程
2 篇 医学
- 2 篇 临床医学
- 1 篇 基础医学(可授医学...
- 1 篇 公共卫生与预防医...
1 篇 理学
- 1 篇 数学
- 1 篇 生物学
- 1 篇 统计学（可授理学、...

主题

15 篇 deep learning
6 篇 machine learning
4 篇 signal processin...
4 篇 training
3 篇 dimensionality r...
3 篇 neural networks
3 篇 speech enhanceme...
3 篇 cnn
2 篇 learning systems
2 篇 representation l...
2 篇 scalability
2 篇 reinforcement le...
2 篇 generalization
2 篇 training data
2 篇 anomaly detectio...
2 篇 graph signal pro...
2 篇 semi-supervised ...
2 篇 information theo...
2 篇 information bott...
2 篇 multitask learni...

机构

2 篇 univ ind santand...
2 篇 univ idaho dept ...
2 篇 yale univ dept g...
2 篇 natl tsing hua u...
2 篇 mila quebec ai i...
2 篇 middle east tech...
2 篇 univ montreal de...
2 篇 yale univ dept c...
2 篇 kings coll londo...
1 篇 csiro astron & s...
1 篇 univ lyon insa l...
1 篇 new york univers...
1 篇 politecn milan m...
1 篇 univ michigan an...
1 篇 univ calif davis...
1 篇 yale univ dept e...
1 篇 friedrich alexan...
1 篇 oticon as dk-276...
1 篇 new york univers...
1 篇 johns hopkins un...

作者

2 篇 tong alexander
2 篇 vural elif
2 篇 simeone osvaldo
2 篇 krishnaswamy smi...
2 篇 xian min
2 篇 jose sharu there...
2 篇 wolf guy
2 篇 arguello henry
2 篇 pei mingtao
2 篇 vakanski aleksan...
2 篇 tan zheng-hua
1 篇 santra a.
1 篇 kalogerias diony...
1 篇 lyu zhaoyan
1 篇 roh si-dong
1 篇 zhang boyu
1 篇 mandayam narayan...
1 篇 yang ming-hsun
1 篇 gramaccioni ricc...
1 篇 andersen lars no...

语言

60 篇 英文
1 篇 其他

检索条件"任意字段=31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021"

共 61 条记录，以下是1-10 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：

2021 ieee 31st international workshop on machine learning for signal processing, mlsp 2021

2021 IEEE 31st International Workshop on Machine Learning fo...

引用

31st ieee international workshop on machine learning for signal processing, mlsp 2021

ISBN: (纸本)9781728163383

The proceedings contain 98 papers. The topics discussed include: hierarchical graph neural nets can capture long-range interactions;self-attention for audio super-resolution;deep complex convolutional recurrent network for multi-channel speech enhancement and dereverberation;model selection of kernel ridge regression for extrapolation;optimizing time domain fully convolutional networks for 3D speech enhancement in a reverberant environment using perceptual losses;online DOA estimation for noninteger linear antenna arrays in coarray domain;tracking of quantized signals based on online kernel regression;and robustness-aware filter pruning for robust neural networks against adversarial attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE NORMALIZED LMP EstIMATION FOR GRAPH signal processing 31

ADAPTIVE NORMALIZED LMP ESTIMATION FOR GRAPH SIGNAL PROCESSI...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Yan, Yi Adel, Radwa Kuruoglu, Ercan E. Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Shenzhen Peoples R China

ISBN: (纸本)9781728163383

We propose an adaptive normalized least mean pth power (GNLMP) algorithm for graph signal processing (GSP), which estimates sampled graph signals under impulsive noise. Compared to the recently introduced adaptive GSP least mean pth power (GLMP) algorithm, the GNLMP algorithm reduces the number of iterations to converge to a steady graph signal. Different from adaptive GSP normalized least mean square (GNLMS) algorithm, the GNLMP algorithm has the ability to reconstruct a graph signal that is corrupted by non-Gaussian noise with heavy-tailed characteristics. Simulations show the performance of the GNLMP algorithm in estimating steady-state and time-varying graph signals, utilizing spectral properties such as bandlimitedness and sampling, faster and more robust in comparison to GLMP and GNLMS.

关键词： Graph signal processing impulsive noise alpha-stable noise normalized least mean pth power algorithm

来源：评论

学校读者我要写书评

暂无评论

BEYOND THE BIAS VARIANCE TRADE-OFF: A MUTUAL INFORMATION TRADE-OFF IN DEEP learning 31

BEYOND THE BIAS VARIANCE TRADE-OFF: A MUTUAL INFORMATION TRA...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Lan, Xinjie Zhu, Bin Boncelet, Charles Barner, Kenneth Univ Delaware Dept Elect & Comp Engn Newark DE 19711 USA

ISBN: (纸本)9781728163383

The classical bias variance trade-off cannot accurately explain how over-parameterized Deep Neural Networks (DNNs) avoid overfitting and achieve good generalization. To address the problem, we alternatively derive a Mutual Information (MI) trade-off based on the recently proposed MI explanation for generalization. In addition, we propose a probabilistic representation of DNNs for accurately estimating the MI. Compared to the classical bias variance trade-off, the MI trade-off not only accurately measures the generalization of over-parameterized DNNs but also formulates the relation between DNN architecture and generalization.

关键词： Generalization Bias variance trade-off Deep learning Information theory

来源：评论

学校读者我要写书评

暂无评论

A UNIFIED PAC-BAYESIAN FRAMEWORK FOR machine UNlearning VIA INFORMATION RISK MINIMIZATION 31

A UNIFIED PAC-BAYESIAN FRAMEWORK FOR MACHINE UNLEARNING VIA ...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Jose, Sharu Theresa Simeone, Osvaldo Kings Coll London Dept Engn Kings Commun Learning & Informat Proc KCLIP Lab London WC2R 2LS England

ISBN: (纸本)9781728163383

machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch. This paper develops a unified PAC-Bayesian framework for machine unlearning that recovers the two recent design principles - variational unlearning [1] and forgetting Lagrangian [2]- as information risk minimization problems [3]. Accordingly, both criteria can be interpreted as PAC-Bayesian upper bounds on the test loss of the unlearned model that take the form of free energy metrics.

关键词： machine unlearning PAC-Bayesian bounds free energy minimization

来源：评论

学校读者我要写书评

暂无评论

ZERO-SHOT MOTION PATTERN RECOGNITION FROM 4D POINT-CLOUDS 31

ZERO-SHOT MOTION PATTERN RECOGNITION FROM 4D POINT-CLOUDS

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Salami, Dariush Sigg, stephan Aalto Univ Dept Commun & Networking Espoo 02150 Finland

ISBN: (纸本)9781728163383

We address a timely and relevant problem in signal processing: The recognition of patterns from spatial data in motion through a zero-shot learning scenario. We introduce a neural network architecture based on Siamese networks to recognize unseen classes of motion patterns. The approach uses a graph-based technique to achieve permutation invariance and also encodes moving point clouds into a representation space in a computationally efficient way. We evaluated the model on an open dataset with twenty-one gestures. The model outperformes state-of-the-art architectures with a considerable margin in four different settings in terms of accuracy while reducing the computational complexity up to 60 times.

关键词： zero-shot learning Siamese network triplet contrastive 4D point cloud gesture recognition

来源：评论

学校读者我要写书评

暂无评论

DEEP LOW-DIMENSIONAL SPECTRAL IMAGE REPRESENTATION FOR COMPRESSIVE SPECTRAL RECONstRUCTION 31

DEEP LOW-DIMENSIONAL SPECTRAL IMAGE REPRESENTATION FOR COMPR...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Monroy, Brayan Bacca, Jorge Arguello, Henry Univ Ind Santander Dept Comp Sci Bucaramanga 680002 Colombia

ISBN: (纸本)9781728163383

Model-based deep learning techniques are the state-of-the-art in compressive spectral imaging reconstruction. These methods integrate deep neural networks (DNN) as spectral image representation used as prior information in the optimization problem, showing optimal results at the expense of increasing the dimensionality of the non-linear representation, i.e., the number of parameters to be recovered. This paper proposes an autoencoder-based network that guarantees a low-dimensional spectral representation through feature reduction, which can be used as prior in the compressive spectral imaging reconstruction. Additionally, based on the experimental observation that the obtained low dimensional spectral representation preserves the spatial structure of the scene, this work exploits the sparsity in the generated feature space by using the Wavelet basis to reduce even more the dimensionally of the inverse problem. The proposed method shows improvements up to 2 dB against state-of-the-art methods.

关键词： Compressive Spectral Imaging Deep learning Recovery Problem Dimension reduction

来源：评论

学校读者我要写书评

暂无评论

AFFINITY MIXUP FOR WEAKLY SUPERVISED SOUND EVENT DETECTION 31

AFFINITY MIXUP FOR WEAKLY SUPERVISED SOUND EVENT DETECTION

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Izadi, Mohammad Rasool stevenson, Robert Kloepper, Laura Univ Notre Dame Notre Dame IN 46556 USA St Marys Coll Notre Dame IN 46556 USA

ISBN: (纸本)9781728163383

The weakly supervised sound event detection (WSSED) problem is the task of predicting the presence of sound events and their corresponding starting and ending points in a weakly labeled dataset. A weak dataset associates each training sample (a short recording) to one or more present sources. Networks that solely rely on convolutional and recurrent layers cannot directly relate multiple frames in a recording. Motivated by attention and graph neural networks, we introduce the concept of an affinity mixup (AM) to incorporate time-level similarities and make a connection between frames. This regularization technique mixes up features in different layers using an adaptive affinity matrix. Our proposed affinity mixup network (AMN) improves over state-of-the-art techniques event-F1 scores by 8:2%.

关键词： Sound event detection weakly supervised learning attention graph

来源：评论

学校读者我要写书评

暂无评论

A CONstRAINED LINEARLY INVOLVED GENERALIZED MOREAU ENHANCED MODEL AND ITS PROXIMAL SPLITTING ALGORITHM 31

A CONSTRAINED LINEARLY INVOLVED GENERALIZED MOREAU ENHANCED ...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Yata, Wataru Yamagishi, Masao Yamada, Isao Tokyo Inst Technol Tokyo Japan

ISBN: (纸本)9781728163383

In this paper, we propose a constrained LiGME (cLiGME) model by incorporating newly multiple convex constraints into the LiGME (Linearly involved Generalized Moreau Enhanced) model which was established recently for many scenarios in sparsity-rank-aware least squares estimation. The cLiGME model can exploit flexibly a priori knowledge on the target to be estimated while keeping the advantage of the LiGME model, i.e., mathematically sound mechanism for nonconvex enhancements of linearly involved convex regularizers. For the cLiGME model, we present a new proximal splitting type algorithm of guaranteed convergence to a global minimizer and demonstrate its effectiveness with a simple numerical experiment.

关键词： Convex optimization Regularized least squares Nonconvex penalties Convex constraints Proximal splitting Moreau enhancement Set theoretic estimation Sparsity-rank-aware signal processing and machine learning

来源：评论

学校读者我要写书评

暂无评论

PRIVACY ASSESSMENT OF FEDERATED learning USING PRIVATE PERSONALIZED LAYERS 31

PRIVACY ASSESSMENT OF FEDERATED LEARNING USING PRIVATE PERSO...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Jourdan, Theo Boutet, Antoine Frindel, Carole Univ Lyon INSA Lyon CREATIS Lyon France Univ Lyon INSA Lyon INRIA CITI Lyon France

ISBN: (纸本)9781728163383

Federated learning (FL) is a collaborative scheme to train a learning model across multiple participants without sharing data. While FL is a clear step forward towards enforcing users' privacy, different inference attacks have been developed. In this paper, we quantify the utility and privacy trade-off of a FL scheme using private personalized layers. While this scheme has been proposed as local adaptation to improve the accuracy of the model through local personalization, it has also the advantage to minimize the information about the model exchanged with the server. However, the privacy of such a scheme has never been quantified. Our evaluations using motion sensor dataset show that personalized layers speed up the convergence of the model and slightly improve the accuracy for all users compared to a standard FL scheme while better preventing both attribute and membership inferences compared to a FL scheme using local differential privacy.

关键词： Privacy Federated learning Inference Attack

来源：评论

学校读者我要写书评

暂无评论

learning-BASED UE CLASSIFICATION IN MILLIMETER-WAVE CELLULAR SYstEMS WITH MOBILITY 31

LEARNING-BASED UE CLASSIFICATION IN MILLIMETER-WAVE CELLULAR...

引用

ieee 31st international workshop on machine learning for signal processing (mlsp)

作者： Pjanic, Dino Sopasakis, Alexandros Tataria, Harsh Tufvesson, Fredrik Reial, Andres Ericsson AB Lund Sweden Lund Univ Dept Elect & Informat Technol Lund Sweden Lund Univ Dept Math Lund Sweden

ISBN: (纸本)9781728163383

Millimeter-wave cellular communication requires beamforming procedures that enable alignment of the transmitter and receiver beams as the user equipment (UE) moves. For efficient beam tracking it is advantageous to classify users according to their traffic and mobility patterns. Research to date has demonstrated efficient ways of machine learning based UE classification. Although different machine learning approaches have shown success, most of them are based on physical layer attributes of the received signal. This, however, imposes additional complexity and requires access to those lower layer signals. In this paper, we show that traditional supervised and even unsupervised machine learning methods can successfully be applied on higher layer channel measurement reports in order to perform UE classification, thereby reducing the complexity of the classification process.

关键词： 5G classification beam management machine learning millimeter-wave mobility

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7页 << < 1 2 3 4 5 6 7 > >>

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：