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

169 篇 会议

馆藏范围

169 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

59 篇 工学
- 58 篇 电气工程
- 57 篇 计算机科学与技术...
- 1 篇 软件工程
56 篇 理学
- 56 篇 物理学

主题

76 篇 signal processin...
58 篇 machine learning
40 篇 signal processin...
39 篇 conferences
25 篇 training
22 篇 deep learning
22 篇 machine learning...
21 篇 accuracy
16 篇 robustness
15 篇 optimization
13 篇 data models
13 篇 standards
12 篇 computational mo...
12 篇 feature extracti...
11 篇 transformers
11 篇 neural networks
10 篇 vectors
8 篇 simulation
8 篇 convolution
8 篇 predictive model...

机构

4 篇 purple mountain ...
4 篇 southeast univ n...
3 篇 national mobile ...
3 篇 purple mt labs p...
2 篇 shanghai jiao to...
2 篇 department of el...
2 篇 indian institute...
2 篇 department of el...
2 篇 univ surrey guil...
2 篇 dept. of electri...
2 篇 school of electr...
2 篇 department of co...
2 篇 imperial coll lo...
2 篇 beijing jiaotong...
2 篇 concordia univ m...
2 篇 shanghai jiao to...
2 篇 department of co...
2 篇 department of el...
2 篇 concordia univer...
2 篇 university of mo...

作者

3 篇 shi jin
2 篇 jean-christophe ...
2 篇 xu xuenan
2 篇 arnaud vandaele
2 篇 george k. atia
2 篇 andrea migliorat...
2 篇 shuchin aeron
2 篇 basil m. idrees
2 篇 geoffrey ye li
2 篇 danilo comminiel...
2 篇 fnu neha
2 篇 ye hao
2 篇 tiziano bianchi
2 篇 wang wenwu
2 篇 jihong park
2 篇 giulia fracastor...
2 篇 jinho choi
2 篇 kevin r. moon
2 篇 ketan rajawat
2 篇 enrico magli

语言

169 篇 英文

检索条件"任意字段=34th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2024"

共 169 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：

34th ieee international workshop on machine learning for signal processing, mlsp 2024 - Proceedings

34th IEEE International Workshop on Machine Learning for Sig...

引用

34th ieee international workshop on machine learning for signal processing, mlsp 2024

ISBN: (纸本)9798350372250

the proceedings contain 121 papers. the topics discussed include: composer style-specific symbolic music generation using vector quantized discrete diffusion models;sparsification of deep neural networks via ternary quantization;orthogonal symmetric nonnegative matrix tri-factorization;convexity based pruning of speech representation models;discriminative community detection for multiplex networks;novel gradient sparsification algorithm via Bayesian inference;adaptive semantic image transmission using generative foundation model;FOLEYGEN: visually-guided audio generation;graph-vector autorregressive model for lithium-ion cell capacity estimation;and episodic fine-tuning prototypical networks for optimization-based few-shot learning: application to audio classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VISUALIZE AND PAINT GAN ACTIVATIONS 34

VISUALIZE AND PAINT GAN ACTIVATIONS

引用

34th international workshop on machine learning for signal processing

作者： Herdt, Rudolf Maass, Peter Univ Bremen Ctr Ind Math D-28334 Bremen Germany

ISBN: (纸本)9798350372267;9798350372250

We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. this gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.

关键词： Deep learning XAI Generative AI GAN Image processing

来源：评论

学校读者我要写书评

暂无评论

NORMALIZING ENERGY CONSUMPTION FOR HARDWARE-INDEPENDENT EVALUATION 34

NORMALIZING ENERGY CONSUMPTION FOR HARDWARE-INDEPENDENT EVAL...

引用

34th international workshop on machine learning for signal processing

作者： Douwes, Constance Serizel, Romain Univ Lorraine LORIA INRIA CNRS Nancy France

ISBN: (纸本)9798350372267;9798350372250

the increasing use of machine learning (ML) models in signal processing has raised concerns about their environmental impact, particularly during resource-intensive training phases. In this study, we present a novel methodology for normalizing energy consumption across different hardware platforms to facilitate fair and consistent comparisons. We evaluate different normalization strategies by measuring the energy used to train different ML architectures on different GPUs, focusing on audio tagging tasks. Our approach shows that the number of reference points, the type of regression and the inclusion of computational metrics significantly influences the normalization process. We find that the appropriate selection of two reference points provides robust normalization, while incorporating the number of floating-point operations and parameters improves the accuracy of energy consumption predictions. By supporting more accurate energy consumption evaluation, our methodology promotes the development of environmentally sustainable ML practices.

关键词： machine learning energy consumption normalization GPU FLOPs signal processing

来源：评论

学校读者我要写书评

暂无评论

ONLINE MULTI-SOURCE DOMAIN ADAPTATION thROUGH GAUSSIAN MIXTURES AND DATASET DICTIONARY learning 34

ONLINE MULTI-SOURCE DOMAIN ADAPTATION THROUGH GAUSSIAN MIXTU...

引用

34th international workshop on machine learning for signal processing

作者： Montesuma, Eduardo Fernandes Le Stanc, Stevan Mboula, Fred Ngole Univ Paris Saclay List CEA F-91120 Palaiseau France Ecole Cent Lyon F-69134 Ecully France

ISBN: (纸本)9798350372267;9798350372250

this paper addresses the challenge of online multi-source domain adaptation (MSDA) in transfer learning, a scenario where one needs to adapt multiple, heterogeneous source domains towards a target domain that comes in a stream. We introduce a novel approach for the online fit of a Gaussian Mixture Model (GMM), based on the Wasserstein geometry of Gaussian measures. We build upon this method and recent developments in dataset dictionary learning for proposing a novel strategy in online MSDA. Experiments on the challenging Tennessee Eastman Process benchmark demonstrate that our approach is able to adapt on the fly to the stream of target domain data. Furthermore, our online GMM serves as a memory, representing the whole stream of data.

关键词： Online learning Optimal Transport Gaussian Mixture Models Domain Adaptation

来源：评论

学校读者我要写书评

暂无评论

ROBUST MEthOD FOR NETWORK TOPOLOGY IDENTIFICATION UNDER STRUCTURAL EQUATION MODEL 34

ROBUST METHOD FOR NETWORK TOPOLOGY IDENTIFICATION UNDER STRU...

引用

34th international workshop on machine learning for signal processing

作者： Yoshida, Kohei Yukawa, Masahiro Keio Univ Dept Elect & Elect Engn Yokohama Kanagawa Japan

ISBN: (纸本)9798350372267;9798350372250

We present a robust method to infer network topology in the presence of outliers from given observations at nodes under the structural equation model. We introduce auxiliary matrices modeling Gaussian noise and sparse outliers. the topology identification task is cast as a minimization problem of the sum of three terms under constraints involving a bilinear form: (i) the squared Frobenius norm of the noise matrix, (ii) the l(1) norm of the adjacency matrix, and (iii) a weakly-convex sparsity-promoting function (the minimax concave penalty) of the outlier matrix. the problem is reformulated into an unconstrained optimization problem by introducing a linear operator, and an efficient alternating minimization method is presented. Simulation results show remarkable robustness of the proposed method.

关键词： graph learning structural equation model outlier robustness operator splitting algorithm

来源：评论

学校读者我要写书评

暂无评论

CONVOLUTIONAL NEURAL NETWORK-BASED RECONSTRUCTION OF BINARIZED ULTRASOUND DATA FOR NON-DESTRUCTIVE TESTING 34

CONVOLUTIONAL NEURAL NETWORK-BASED RECONSTRUCTION OF BINARIZ...

引用

34th international workshop on machine learning for signal processing

作者： Moreau, Alexandre Bouchard, Angelique Subakan, Gem Painchaud-April, Guillaume Le Duff, Alain Univ Laval Quebec City PQ Canada Evident Sci Montreal PQ Canada Concordia Univ Montreal PQ Canada Mila Quebec AI Inst Montreal PQ Canada

ISBN: (纸本)9798350372267;9798350372250

this article introduces an exploratory project focused on reconstructing original ultrasound data from binarized observations as used in the Phase Coherence Imaging (PCI) method proposed by [1]. the PCI method, gaining popularity in the field of non-destructive testing, involves extracting only the phase information from the data while discarding amplitude details. the challenge of reconstructing the original data from its binarized form shares similarities with well-known machine learning tasks, such as image colorization, which is fundamentally an ill-posed problem. In this project, we investigate techniques inspired by approaches commonly used for addressing these tasks. Using the popular U-Net architecture, we show that the complete ultrasound signal can be reconstructed from the phase information that remains in the binarized signal used for the PCI representation, which is easy to store and process in a portable device.

关键词： NDE NDT Ultrasound PCI signal processing CNN mlsp

来源：评论

学校读者我要写书评

暂无评论

ON thE DYNAMICS OF MULTIAGENT NONLINEAR FILTERING AND learning 34

ON THE DYNAMICS OF MULTIAGENT NONLINEAR FILTERING AND LEARNI...

引用

34th international workshop on machine learning for signal processing

作者： Talebi, Sayed Pouria Mandic, Danilo P. Univ Roehampton Comp Sci Dept London SW15 5PH England Imperial Coll London Elect & Elect Engn Dept London SW7 2AZ England

ISBN: (纸本)9798350372267;9798350372250

Multiagent systems aim to accomplish highly complex learning tasks through decentralised consensus seeking dynamics. In the past decade, use of the multiagent framework either in the form of federated learning or distributed estimation has garnered a great deal of attention in the signal processing and computational intelligence societies. this article examines behaviour of multiagent networked systems that use nonlinear filtering/learning frameworks. this article considers the most general learning framework that is reliant on multiple input streams. Operations of this centralised framework is decomposed into operations corresponding to the federated and distributed frameworks. this decomposition process is used to formulate the changes in learning dynamics as the framework shifts from centralised to distributed. Importantly, the formulated dynamics indicate convergence conditions of distributed learning techniques are much more relaxed than formerly considered.

关键词： Multiagent systems nonlinear dynamics federated/distributed learning convergence and stability

来源：评论

学校读者我要写书评

暂无评论

SELF SUPERVISED DICTIONARY learning USING KERNEL MATCHING 34

SELF SUPERVISED DICTIONARY LEARNING USING KERNEL MATCHING

引用

34th international workshop on machine learning for signal processing

作者： Choudhary, Shubham Masset, Paul Ba, Demba Harvard Univ Sch Engn & Appl Sci Cambridge MA 02138 USA Harvard Univ Kempner Inst Study Nat & Artificial Intelligence Cambridge MA 02138 USA McGill Univ Dept Psychol Montreal PQ Canada

ISBN: (纸本)9798350372267;9798350372250

We introduce a self supervised framework for learning representations in the context of dictionary learning. We cast the problem as a kernel matching task between the input and the representation space, with constraints on the latent kernel. By adjusting these constraints, we demonstrate how the framework can adapt to different learning objectives. We then formulate a novel Alternate Direction Method of Multipliers (ADMM) based algorithm to solve the optimization problem and connect the dynamics to classical alternate minimization techniques. this approach offers a unique way of learning representations with kernel constraints, that enable us implicitly learn a generative map for the data from the learned representations which can have broad applications in representation learning tasks both in machine learning and neuroscience.

关键词： Dictionary learning Kernel Matching Self-Supervised Sparse coding Manifold learning

来源：评论

学校读者我要写书评

暂无评论

COLLABORATIVE learning FOR LESS ONLINE RETRAINING OF NEURAL RECEIVERS 34

COLLABORATIVE LEARNING FOR LESS ONLINE RETRAINING OF NEURAL ...

引用

34th international workshop on machine learning for signal processing

作者： Wang, Tianxin Wang, Shuo Wang, Xudong Li, Geoffrey Ye Shanghai Jiao Tong Univ Shanghai Peoples R China Imperial Coll London London England

ISBN: (纸本)9798350372267;9798350372250

Offline-trained neural receivers achieve significant performance gains. Yet, online retraining is required to sustain such gains in a new environment. Instead of retraining whenever a new channel environment arises, a multi-cell collaborative learning framework is designed to enable the neural receivers to generalize to unseen scenarios, thus preventing frequent retraining. this framework features two key designs: 1) the personalized federated learning paradigm is exploited to strike a generalization-personalization balance, with each model sharing a global representation network and personalizing the local head network;2) an online data filtering mechanism is designed to filter out low-impact data samples. According to simulations, the collaboratively-learned receivers outperform the traditional ones by over 3 dB and improves the generalization performance by 5.2 dB in the unseen scenarios.

关键词： Personalized federated learning neural receiver online collaboration

来源：评论

学校读者我要写书评

暂无评论

COLLABORATIVE learning FOR INCREMENTAL CLASSIFICATION OF EMG signalS 34

COLLABORATIVE LEARNING FOR INCREMENTAL CLASSIFICATION OF EMG...

引用

34th international workshop on machine learning for signal processing

作者： Moore, Karl Ibunu, Shamahil Alty, Stephen R. Took, Clive Cheong Royal Holloway Univ London Dept Elect Engn Egham Hill Egham TW20 0EX Surrey England

ISBN: (纸本)9798350372267;9798350372250

In this work, we address the problem of online learning for electromyogram (EMG) classification. the main challenge of EMG is its streaming nature, which implies that not all data are available at once. As such, offline and batch methods such as deep learning are generally not appropriate for such small data. To address this problem, we propose an incremental learning technique whereby the algorithm enhances its knowledge about the data progressively, as it receives new data. Moreover, we propose to employ multiple learners (instead of a single learner);each learning and focusing on a specific class. this federated learning strategy in incremental learning shows superior performance over both existing incremental learning and deep learning methods in our simulation studies on small data.

关键词： Electromyogram collaborative learning incremental learning

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17页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：