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

907 篇 期刊文献
618 篇 会议
12 篇 学位论文

馆藏范围

1,537 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,386 篇 工学
- 946 篇 计算机科学与技术...
- 488 篇 电气工程
- 177 篇 信息与通信工程
- 129 篇 控制科学与工程
- 128 篇 软件工程
- 75 篇 生物医学工程（可授...
- 73 篇 仪器科学与技术
- 59 篇 机械工程
- 48 篇 材料科学与工程（可...
- 36 篇 电子科学与技术（可...
- 32 篇 石油与天然气工程
- 25 篇 测绘科学与技术
- 24 篇 化学工程与技术
- 21 篇 土木工程
- 21 篇 环境科学与工程（可...
- 19 篇 动力工程及工程热...
- 17 篇 力学（可授工学、理...
- 16 篇 交通运输工程
- 13 篇 生物工程
327 篇 理学
- 124 篇 物理学
- 95 篇 生物学
- 59 篇 化学
- 54 篇 数学
- 35 篇 地球物理学
- 20 篇 统计学（可授理学、...
243 篇 医学
- 146 篇 临床医学
- 61 篇 特种医学
- 56 篇 基础医学(可授医学...
109 篇 管理学
- 88 篇 管理科学与工程(可...
- 15 篇 图书情报与档案管...
18 篇 农学
12 篇 经济学
10 篇 法学
10 篇 教育学
9 篇 文学
3 篇 艺术学

主题

1,537 篇 variational auto...
260 篇 deep learning
131 篇 anomaly detectio...
93 篇 machine learning
59 篇 generative adver...
47 篇 generative model
46 篇 training
43 篇 feature extracti...
42 篇 unsupervised lea...
39 篇 neural networks
37 篇 representation l...
36 篇 generative adver...
36 篇 data augmentatio...
34 篇 convolutional ne...
33 篇 data models
27 篇 semi-supervised ...
27 篇 artificial intel...
26 篇 task analysis
26 篇 deep generative ...
25 篇 collaborative fi...

机构

10 篇 natl chiao tung ...
6 篇 ucl england
6 篇 shenzhen univ co...
6 篇 shanghai univ sc...
5 篇 nanyang technol ...
5 篇 zhejiang lab peo...
5 篇 xiamen univ sch ...
5 篇 chung yuan chris...
4 篇 mit comp sci & a...
4 篇 univ chinese aca...
4 篇 beijing jiaotong...
4 篇 acad sinica res ...
4 篇 acad sinica taiw...
4 篇 oak ridge natl l...
4 篇 northwestern pol...
4 篇 ecole technol su...
4 篇 chongqing univ p...
4 篇 tsinghua univ de...
4 篇 univ elect sci &...
4 篇 zhejiang univ st...

作者

12 篇 chien jen-tzung
8 篇 tahan antoine
8 篇 chen junghui
8 篇 zemouri ryad
7 篇 yang fan
7 篇 utschick wolfgan...
7 篇 zhang hao
6 篇 tsao yu
6 篇 baur michael
6 篇 slavic giulia
6 篇 wang hsin-min
6 篇 regazzoni carlo
6 篇 marcenaro lucio
5 篇 guo rui
5 篇 li maokun
5 篇 hsu wei-ning
5 篇 glass james
5 篇 liu xin
5 篇 yoshii kazuyoshi
5 篇 li yan

语言

1,489 篇 英文
38 篇 其他
2 篇 中文
1 篇 德文
1 篇 法文
1 篇 意大利文
1 篇 朝鲜文
1 篇 土耳其文

检索条件"主题词=Variational autoencoder"

共 1537 条记录，以下是1201-1210 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：

Cardiac MRI Segmentation with Strong Anatomical Guarantees 22nd

Cardiac MRI Segmentation with Strong Anatomical Guarantees

引用

10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Painchaud, Nathan Skandarani, Youssef Judge, Thierry Bernard, Olivier Lalande, Alain Jodoin, Pierre-Marc Univ Sherbrooke Dept Comp Sci Sherbrooke PQ Canada Univ Bourgogne Franche Comte Dijon France Univ Lyon Lyon France

ISBN: (纸本)9783030322458;9783030322441

Recent publications have shown that the segmentation accuracy of modern-day convolutional neural networks (CNN) applied on cardiac MRI can reach the inter-expert variability, a great achievement in this area of research. However, despite these successes, CNNs still produce anatomically inaccurate segmentations as they provide no guarantee on the anatomical plausibility of their outcome, even when using a shape prior. In this paper, we propose a cardiac MRI segmentation method which always produces anatomically plausible results. At the core of the method is an adversarial variational autoencoder (aVAE) whose latent space encodes a smooth manifold on which lies a large spectrum of valid cardiac shapes. This aVAE is used to automatically warp anatomically inaccurate cardiac shapes towards a close but correct shape. Our method can accommodate any cardiac segmentation method and convert its anatomically implausible results to plausible ones without affecting its overall geometric and clinical metrics. With our method, CNNs can now produce results that are both within the inter-expert variability and always anatomically plausible.

关键词： CNN variational autoencoder Cardiac MRI segmentation

来源：评论

学校读者我要写书评

暂无评论

Transfer learning of the expressivity using FLOW metric learning in multispeaker text-to-speech synthesis 21

Transfer learning of the expressivity using FLOW metric lear...

引用

Interspeech Conference

作者： Kulkarni, Ajinkya Colotte, Vincent Jouvet, Denis Univ Lorraine CNRS INRIA LORIA F-54000 Nancy France

ISBN: (纸本)9781713820697

In this paper, we present a novel flow metric learning architecture in a parametric multispeaker expressive text-to-speech (TTS) system. We proposed inverse autoregressive flow (IAF) as a way to perform the variational inference, thus providing flexible approximate posterior distribution. The proposed approach condition the text-to-speech system on speaker embeddings so that latent space represents the emotion as semantic characteristics. For representing the speaker, we extracted speaker embeddings from the x-vector based speaker recognition model trained on speech data from many speakers. To predict the vocoder features, we used the acoustic model conditioned on the textual features as well as on the speaker embedding. We transferred the expressivity by using the mean of the latent variables for each emotion to generate expressive speech in different speaker's voices for which no expressive speech data is available. We compared the results obtained using flow-based variational inference with variational autoencoder as a baseline model. The performance measured by mean opinion score (MOS), speaker MOS, and expressive MOS shows that N-pair loss based deep metric learning along with IAF model improves the transfer of expressivity in the desired speaker's voice in synthesized speech.

关键词： text-to-speech variational autoencoder inverse autoregressive flow deep metric learning expressivity

来源：评论

学校读者我要写书评

暂无评论

LEARNING LATENT REPRESENTATIONS FOR STYLE CONTROL AND TRANSFER IN END-TO-END SPEECH SYNTHESIS 44

LEARNING LATENT REPRESENTATIONS FOR STYLE CONTROL AND TRANSF...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Ya-Jie Pan, Shifeng He, Lei Ling, Zhen-Hua Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China Microsoft China Beijing Peoples R China Microsoft STC Asia Beijing Peoples R China

ISBN: (纸本)9781479981311

In this paper, we introduce the variational autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good properties such as disentangling, scaling, and combination, which makes it easy for style control. Style transfer can be achieved in this framework by first inferring style representation through the recognition network of VAE, then feeding it into TTS network to guide the style in synthesizing speech. To avoid Kullback-Leibler (KL) divergence collapse in training, several techniques are adopted. Finally, the proposed model shows good performance of style control and outperforms Global Style Token (GST) model in ABX preference tests on style transfer.

关键词： unsupervised learning variational autoencoder style transfer speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Learning Disentangled User Representation Based on Controllable VAE for Recommendation 26th

Learning Disentangled User Representation Based on Controlla...

引用

26th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Li, Yunyi Zhao, Pengpeng Wang, Deqing Xian, Xuefeng Liu, Yanchi Sheng, Victor S. Soochow Univ Inst Artificial Intelligence Sch Comp Sci & Technol Suzhou Peoples R China Beihang Univ Suzhou Peoples R China Suzhou Vocat Univ Suzhou Peoples R China NEC Labs Amer Princeton NJ USA Texas Tech Univ Dept Comp Sci Lubbock TX USA

ISBN: (纸本)9783030731991;9783030732004

User behaviour on purchasing is always driven by complex latent factors, which are highly disentangled in the real world. Learning latent factorized representation of users can uncover user intentions behind the observed data (i.e. user-item interaction) and improve the robustness and interpretability of the recommender system. However, existing collaborative filtering methods learning disentangled representation face problems of balancing the trade-off between reconstruction quality and disentanglement. In this paper, we propose a controllable variational autoencoder framework for collaborative filtering. Specifically, we adopt a modified Proportional-Integral-Derivative (PID) control to the beta-VAE objective to automatically tune the hyperparameter beta using the output of Kullback-Leibler divergence as feedback. We further introduce item embeddings to guide the system to learn representation related to the real-world concepts using a factorized Gaussian distribution. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines. We further evaluate our model's effectiveness to control the trade-off between reconstruction error and disentanglement quality in the recommendation.

关键词： variational autoencoder Disentangled representation learning Recommender system

来源：评论

学校读者我要写书评

暂无评论

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer 24

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis...

引用

Interspeech Conference

作者： Zhang, Yongmao Xue, Heyang Li, Hanzhao Xie, Lei Guo, Tingwei Zhang, Ruixiong Gong, Caixia Northwestern Polytech Univ Audio Speech & Language Proc Grp ASLP NPU Sch Comp Sci Xian Peoples R China DiDi Chuxing Beijing Peoples R China

End-to-end singing voice synthesis (SVS) model VISinger [1] can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problems: text-to-phase problem, the end-to-end model learns the meaningless mapping of text-to-phase;glitches problem, the harmonic components corresponding to the periodic signal of the voiced segment occurs a sudden change with audible artefacts;low sampling rate, the sampling rate of 24KHz does not meet the application needs of high-fidelity generation with the full-band rate (44.1KHz or higher). In this paper, we propose VISinger 2 to address these issues by integrating the digital signal processing (DSP) methods with VISinger. Specifically, inspired by recent advances in differentiable digital signal processing (DDSP) [2], we incorporate a DSP synthesizer into the decoder to solve the above issues. The DSP synthesizer consists of a harmonic synthesizer and a noise synthesizer to generate periodic and aperiodic signals, respectively, from the latent representation z in VISinger. It supervises the posterior encoder to extract the latent representation without phase information and avoid the prior encoder modelling text-to-phase mapping. To avoid glitch artefacts, the HiFiGAN is modified to accept the waveforms generated by the DSP synthesizer as a condition to produce the singing voice. Moreover, with the improved waveform decoder, VISinger 2 manages to generate 44.1kHz singing audio with richer expression and better quality. Experiments on OpenCpop corpus [3] show that VISinger 2 outperforms VISinger, CpopSing and RefineSinger in both subjective and objective metrics. Our audio samples and source code are available (1).

关键词： Singing voice synthesis variational autoencoder adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Instance Segmentation with a Learned Shape Prior 3rd

Semi-supervised Instance Segmentation with a Learned Shape P...

引用

3rd Int Workshop on Interpretabil of Machine Intelligence in Med Image Comp / 2nd Int Workshop on Med Image Learning with Less Labels and Imperfect Data / 5th Int Workshop on Largescale Annotat of Biomed Data and Expert Label Synthesis

作者： Chen, Long Zhang, Weiwen Wu, Yuli Strauch, Martin Merhof, Dorit Rhein Westfal TH Aachen Inst Imaging & Comp Vis Aachen Germany

ISBN: (纸本)9783030611651;9783030611668

To date, most instance segmentation approaches are based on supervised learning that requires a considerable amount of annotated object contours as training ground truth. Here, we propose a framework that searches for the target object based on a shape prior. The shape prior model is learned with a variational autoencoder that requires only a very limited amount of training data: In our experiments, a few dozens of object shape patches from the target dataset, as well as purely synthetic shapes, were sufficient to achieve results en par with supervised methods with full access to training data on two out of three cell segmentation datasets. Our method with a synthetic shape prior was superior to pre-trained supervised models with access to limited domain-specific training data on all three datasets. Since the learning of prior models requires shape patches, whether real or synthetic data, we call this framework semi-supervised learning. The code is available to the public (https://***/looooongChen/shape_prior_seg).

关键词： Semi-supervised Instance segmentation Shape prior variational autoencoder Edge loss

来源：评论

学校读者我要写书评

暂无评论

Deep variational auto-encoders for unsupervised glomerular classification

Deep variational auto-encoders for unsupervised glomerular c...

引用

SPIE Medical Imaging Symposium / 6th Digital Pathology Conference

作者： Lutnick, Brendon Yacoub, Rabi Jen, Kuang-Yu Tomaszewski, John E. Jain, Sanjay Sarder, Pinaki SUNY Buffalo Dept Pathol & Anat Sci Buffalo NY 14260 USA SUNY Buffalo Med Nephrol Buffalo NY USA Univ Calif Davis Dept Pathol Davis CA 95616 USA Washington Univ Sch Med Dept Med Nephrol St Louis MO 63130 USA

ISBN: (数字)9781510616523

ISBN: (纸本)9781510616523

The adoption of deep learning techniques in medical applications has thus far been limited by the availability of the large labeled datasets required to robustly train neural networks, as well as difficulty interpreting these networks. However, recent techniques for unsupervised training of neural networks promise to address these issues, leveraging only structure to model input data. We propose the use of a variational autoencoder (VAE) which utilizes data from an animal model to augment the training set and non-linear dimensionality reduction to map this data to human sets. This architecture utilizes variational inference, performed on latent parameters, to statistically model the probability distribution of training data in a latent feature space. We show the feasibility of VAEs, using images of mouse and human renal glomeruli from various pathological stages of diabetic nephropathy (DN), to model the progression of structural changes which occur in DN. When plotted in a 2-dimentional latent space, human and mouse glomeruli, show separation with some overlap, suggesting that the data is continuous, and can be statistically correlated. When DN stage is plotted in this latent space, trends in disease pathology are visualized.

关键词： Cross species modeling knowledge transfer variational autoencoder unsupervised modeling

来源：评论

学校读者我要写书评

暂无评论

Comparing Beta-VAE toWGAN-GP for Time Series Augmentation to Improve Classification Performance 14th

Comparing Beta-VAE toWGAN-GP for Time Series Augmentation to...

引用

14th International Conference on Agents and Artificial Intelligence (ICAART)

作者： Kavran, Domen Zalik, Borut Lukac, Niko Univ Maribor Fac Elect Engn & Comp Sci Koroska Cesta 46 Maribor Slovenia

ISBN: (纸本)9783031229527;9783031229534

Datasets often lack diversity to train robust classification models, capable of being used in real-life scenarios. Neural network-based generative models learn characteristics to generate synthetic (i.e. augmented) data, with the goal of increasing the diversity in datasets. A comparison is presented between Beta-VAE and WGAN-GP as ResNet-18 based generative time series models. The proposed generative models were tested on benchmark datasets to observe the effects of synthetic sets on the improvement in time series classification performance. Experiments were performed using 1-nearest neighbor algorithm and the state-of-the-art classification method MiniRocket. The choice of synthetic set size must be performed empirically to maximise the classification performance. By choosing the best synthetic set size for each dataset, the Beta-VAE generated synthetic sets led to an average increase in classification accuracy of +0,722% when used in the 1-nearest neighbor algorithm, and +1,856% when used for training the MiniRocket. The use ofWGAN-GP generated synthetic sets to train classifiers led to average increases in classification accuracy of +0,654% with the 1-nearest neighbor algorithm and +1,753% with MiniRocket. The highest achieved increases in accuracy with the use of Beta-VAE and WGAN-GP generated synthetic sets were +6,84% and +10,53%, respectively.

关键词： Time series Augmentation Classification variational autoencoder Generative adversarial network Beta-VAE WGAN-GP

来源：评论

学校读者我要写书评

暂无评论

Trace Data Analytics with Knowledge Distillation DM: Big Data Management and Mining 31

Trace Data Analytics with Knowledge Distillation DM: Big Dat...

引用

31st Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC)

作者： Lee, Janghwan Xiong, Wei Jang, Wonhyouk Samsung Elect Samsung Display Amer Lab San Jose CA 95134 USA Samsung Display Display Res Ctr Yongin South Korea

ISBN: (纸本)9781728158761

In this paper, we propose the "trace data analytics" for classifying fault conditions from multivariate time series sensor signals using well-known deep CNN models. In our approach, multiple sensor signals are converted into two dimensional representations using the proposed conversion methods to optimize the classification performance. Many studies on the prediction of manufacturing results using sensor signals have been conducted in the field of fault detection and classification for display and semiconductor manufacturing processes. It is challenging to apply machine learning to real-life manufacturing problems due to practical limitations, class imbalance and data insufficiency, which also make it difficult to produce a generalized model. To overcome these challenges, we propose using omni-supervised learning but with a new approach to knowledge distillation that ensembles predictions from multiple instantiations of a CNN model of synthetically generated data samples from a deep generative model. Our experiment results show that the fault classification accuracy improves substantially by applying trace data analytics to manufacturing data from display fabrication lines. The results also show that the quality of trained CNN models using the proposed knowledge distillation is maintained steadily and stably.

关键词： Fault classification Semi-supervised learning variational autoencoder display manufacturing knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Quantifying Common Support between Multiple Treatment Groups Using a Contrastive-VAE 6

Quantifying Common Support between Multiple Treatment Groups...

引用

6th Machine Learning for Health (ML4H) Workshop - Advancing Healthcare for All as a part of NeurIPS Conference

作者： Dai, Wangzhi Stultz, Collin M. MIT Cambridge MA 02139 USA Massachusetts Gen Hosp Boston MA 02114 USA

Estimating the effect of a given medical treatment on individual patients involves evaluating how clinical outcomes are affected by the treatment in question. Robust estimates of the treatment effect for a given patient with a pre-specified set of clinical characteristics, are possible to obtain when there is sufficient common support for these features. Essentially, features having the greatest common support correspond to regions of significant overlap between the distributions of the different treatment groups. In observational datasets, however, all possible treatment options may not be uniformly represented, and therefore robust estimation of their effect may only be possible for the patients in the overlapping region. In this work, we propose a Contrastive variational autoencoder (Contrastive-VAE) to estimate where there is significant overlap between patient distributions corresponding to different treatment options. A Contrastive-VAE exploits shared information between different groups by modeling the shared information as arising from a shared set of latent variables to approximate distributions for treatment options that are not well represented in observational datasets. The result is an improved estimation of the distribution of the groups with a small number of data points. By estimating the likelihood for each group with annealed importance sampling, we are able to quantitatively identify the area of overlap between multiple treatment groups and obtain an effective confidence interval for the estimated individual treatment effect.

关键词： Common Support Contrastive Learning variational autoencoder

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154页 << < 117 118 119 120 121 122 123 124 125 126 > >>

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：