检索结果-内蒙古大学图书馆

IEEE Conference on Energy Internet and Energy System Integration

作者： Xiying Gao Ning Ye Jinchun Song Haomiao Wang Ye Zhang Yan Guan Xiaowen Song Yingkai Cai Wenshu Zhang Qian Hui Dan Li State Grid Liaoning Electric Power Research Institute Shenyang China The School of Mechanical Engineering and Automation Northeastern University Shenyang China State Grid Liaoning Electric Power Marketing Department Shenyang China State Grid Liaoyang Electric Power B&E Office Liaoyang China

In this paper, we propose a method for performing electricity price execution inspection by using a variational autoencoder technology in deep learning. The variational autoencoder based anomaly detection algorithm (VABAD) can be used both as a discriminant model and as a feature of the generation model, which effectively solves the calculation problem of multiple heterogeneous parameters of current electricity price inspection implementation. The reconstruction probability is a probabilistic measure that takes into account the variability of the distribution of variables. It is used by autoencoder based anomaly detection methods. Experimental results show that the proposed method has been validated and compared to the existing approaches. The databases used in this paper come from Power Marketing System that occurred in Liaoning, China in 2015.

关键词： Deep learning variational autoencoder Electricity price inspection implementation Data heterogeneity

来源：评论

学校读者我要写书评

暂无评论

Statistical Speech Enhancement Based on Probabilistic Integration of variational autoencoder and Non-Negative Matrix Factorization

Statistical Speech Enhancement Based on Probabilistic Integr...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Yoshiaki Bando Masato Mimura Katsutoshi Itoyama Kazuyoshi Yoshii Tatsuya Kawahara Graduate School of Informatics Kyoto University Sakyo-ku Kyoto 606-8501 Japan

ISBN: (纸本)9781538646595

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervised approach requires a very large amount of pair data for training, it is not robust against unknown environments. Another approach is to use non-negative matrix factorization (NMF) based on basis spectra trained on clean speech in advance and those adapted to noise on the fly. This semi-supervised approach, however, causes considerable signal distortion in enhanced speech due to the unrealistic assumption that speech spectrograms are linear combinations of the basis spectra. Replacing the poor linear generative model of clean speech in NMF with a VAE-a powerful nonlinear deep generative model-trained on clean speech, we formulate a unified probabilistic generative model of noisy speech. Given noisy speech as observed data, we can sample clean speech from its posterior distribution. The proposed method outperformed the conventional DNN-based method in unseen noisy environments.

关键词： Single-channel speech enhancement variational autoencoder Bayesian signal processing Speech Speech enhancement Noise matrix decomposition NMF protocol Unknown environments factorization Signal distortion

来源：评论

学校读者我要写书评

暂无评论

UNSUPERVISED DOMAIN ADAPTATION FOR ROBUST SPEECH RECOGNITION VIA variational autoencoder-BASED DATA AUGMENTATION

UNSUPERVISED DOMAIN ADAPTATION FOR ROBUST SPEECH RECOGNITION...

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Hsu, Wei-Ning Zhang, Yu Glass, James MIT Comp Sci & Artificial Intelligence Lab 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9781509047888

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world applications. Research on robust speech recognition can be regarded as trying to overcome this domain mismatch issue. In this paper, we address the unsupervised domain adaptation problem for robust speech recognition, where both source and target domain speech are available, but word transcripts are only available for the source domain speech. We present novel augmentation-based methods that transform speech in a way that does not change the transcripts. Specifically, we first train a variational autoencoder on both source and target domain data (without supervision) to learn a latent representation of speech. We then transform nuisance attributes of speech that are irrelevant to recognition by modifying the latent representations, in order to augment labeled training data with additional data whose distribution is more similar to the target domain. The proposed method is evaluated on the CHiME-4 dataset and reduces the absolute word error rate (WER) by as much as 35% compared to the non-adapted baseline.

关键词： unsupervised domain adaptation robust speech recognition variational autoencoder data augmentation

来源：评论

学校读者我要写书评

暂无评论

Hidden Markov Model variational autoencoder for Acoustic Unit Discovery 18

Hidden Markov Model Variational Autoencoder for Acoustic Uni...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Ebbers, Janek Heymann, Jahn Drude, Lukas Glarner, Thomas Haeb-Umbach, Reinhold Raj, Bhiksha Paderborn Univ Paderborn Germany Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781510848764

variational autoencoders (VAEs) have been shown to provide efficient neural-network-based approximate Bayesian inference for observation models for which exact inference is intractable. Its extension. the so-called Structured VAE (SVAE) allows inference in the presence of both discrete and continuous latent variables. Inspired by this extension, we developed a VAE with Hidden Markov Models (HMMs) as latent models. We applied the resulting HMM-VAE to the task of acoustic unit discovery in a zero resource scenario. Starting from an initial model based on variational inference in an HMM with Gaussian Mixture Model (GMM) emission probabilities, the accuracy of the acoustic unit discovery could be significantly improved by the HMM-VAE. In doing so we were able to demonstrate for an unsupervised learning task what is well-known in the supervised learning case: Neural networks provide superior modeling power compared to GMMs.

关键词： variational autoencoder hidden Markov Model unsupervised learning acoustic unit discovery

来源：评论

学校读者我要写书评

暂无评论

The Difference Learning of Hidden Layer between autoencoder and variational autoencoder 29

The Difference Learning of Hidden Layer between Autoencoder ...

引用

第29届中国控制与决策会议

作者： Qingyang Xu Zhe Wu Yiqin Yang Li Zhang School of Mechanical Electrical & Information EngineeringShandong University

ISBN: (纸本)9781509046584

autoencoder is an excellent unsupervised learning ***,it can not generate kinds of sample data in the decoding *** autoencoder is a typical generative adversarial net which can generate various data to augment the sample *** this paper,we want to do some research about the information learning in hidden *** the simulation,we compare the hidden layer learning of hidden layer in conventional autoencoder and variational autoencoder.

关键词： autoencoder variational autoencoder Hidden layer learning Probabilistic model MNIST

来源：评论

学校读者我要写书评

暂无评论

Different Latent Variables Learning in variational autoencoder

Different Latent Variables Learning in Variational Autoencod...

引用

4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS)

作者： Xu, Qingyang Yang, Yiqin Wu, Zhe Zhang, Li Shandong Univ Sch Mech Elect & Informat Engn Weihai 264209 Peoples R China

ISBN: (纸本)9781538632574

Unsupervised learning is a good neural network training way. However, the unsupervised learning algorithm is rare. The generative model is an interesting algorithm which can generate the similar data as the sample data by building a probabilistic model of the input data, and it can be used for unsupervised learning. variational autoencoder is a typical generative model which is different from common autoencoder that a probabilistic parameter layer follows the hidden layer. Some new data can be reconstructed according to probabilistic model parameters. The probabilistic model parameter is the latent variable. In this paper, we want to do some research to test the data reconstruct effect of the variational autoencoder by different latent variables. According to the simulation, the more latent variables the more style of the sample is.

关键词： variational autoencoder probabilistic model latent Variable MNIST

来源：评论

学校读者我要写书评

暂无评论

Traffic Identification of Mobile Apps Based on variational autoencoder Network 13

Traffic Identification of Mobile Apps Based on Variational A...

引用

13th International Conference on Computational Intelligence and Security (CIS)

作者： Li, Ding Zhu, Yuefei Lin, Wei Informat Engn Univ Zhengzhou Henan Peoples R China

ISBN: (纸本)9781538648223

Traffic identification is a fundamental issue in network security. Traditional methods, such as depth packet inspection (DPI) and flow-based classifiers, have difficulties in labeling massive samples and extracting features manually. Motivated by the achievements in computer vision, we focus on mobile app traffic, proposing a deep learning model based on variational autoencoder network (VEAN). Our contributions are two-fold. First, we propose a novel method of transforming mobile app traffic flows into vision-meaningful images, and thus enable the machine to identify the traffic in a human way. Then, based on the transformation method, we create an open dataset named IMTD17. Second, an improved network model is proposed, where variational autoencoder (VAE) algorithm is introduced into a two-stage learning. The model realizes the learning from massive unlabeled data, and the feasibility of the replacement for manual feature extraction is illustrated by the visualization analysis of the latent features. The experimental results show that the identification accuracy can reach 99.6%, which satisfies the practical requirement.

关键词： traffic identification mobile app latent feature variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

The Character Generation in Handwriting Feature Extraction using variational autoencoder 14

The Character Generation in Handwriting Feature Extraction u...

引用

14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Yamada, Tomoki Hosoe, Mariko Kato, Kunihito Yamamoto, Kazuhiko Gifu Univ Fac Engn Gifu Japan Forens SciLab Gifu PrefPolice HQ Gifu Prefectural Police Headquarters Gifu Japan

ISBN: (纸本)9781538635865

Handwriting identification is a method to identify an unknown writer by comparing a known writer's characters with an unknown writer's characters by using the homeostasis of handwriting in the characters. In handwriting identification, improving the accuracy is important in analyzing a large number of characters of the same class. However, a problem with the accuracy of handwriting identification occurs because of lack of characters of the same class. In order to solve this problem, we propose a method of extracting features of handwritten characters from a character class and generating characters of different character class based on the extracted features. It is difficult to extract handwriting features by scientific numerical analysis method, and to generate characters from extracted handwriting features. In this paper, we tried to construct a learning method using Deep Learning to generate a model of the handwriting feature extraction and the handwriting character data generative model. Using the existing neural network model, we tried to apply the generative model of the data of Japanese characters (Hiragana). Because existing models cannot capture complicated character features like Hiragana, we propose a modified method to improve character generation accuracy by adding a convolution model to the existing neural network model. Improvement of character generation accuracy by adding the convolution model was confirmed by using quantitative evaluation method of generated characters.

关键词： variational autoencoder Generative model Character generation

来源：评论

学校读者我要写书评

暂无评论

Connections with robust PCA and the role of emergent sparsity in variational autoencoder models

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2018年第1期19卷

作者： Bin Dai Yu Wang John Aston Gang Hua David Wipf Institute for Advanced Study Tsinghua University Beijing China Department of Pure Mathematics and Mathematical Statistics University of Cambridge Cambridge UK Microsoft Research Redmond Microsoft Research Beijing China

variational autoencoders (VAE) represent a popular, exible form of deep generative model that can be stochastically _t to samples from a given random process using an information-theoretic variational bound on the true underlying distribution. Once so-obtained, the model can be putatively used to generate new samples from this distribution, or to provide a low-dimensional latent representation of existing samples. While quite effective in numerous application domains, certain important mechanisms which govern the behavior of the VAE are obfuscated by the intractable integrals and resulting stochastic approximations involved. Moreover, as a highly non-convex model, it remains unclear exactly how minima of the underlying energy relate to original design purposes. We attempt to better quantify these issues by analyzing a series of tractable special cases of increasing complexity. In doing so, we unveil interesting connections with more traditional dimensionality reduction models, as well as an intrinsic yet underappreciated propensity for robustly dismissing sparse outliers when estimating latent manifolds. With respect to the latter, we demonstrate that the VAE can be viewed as the natural evolution of recent robust PCA models, capable of learning nonlinear manifolds of unknown dimension obscured by gross corruptions.

关键词： deep generative model robust PCA variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

variational Type Graph autoencoder for Denoising on Event Recommendation

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2025年第1期43卷 1-27页

作者： Zhang, Shuo Meng, Xiangwu Zhang, Yujie Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing Key Lab Intelligent Telecommun Software & Beijing Peoples R China

Recommendations for events play a pivotal role in facilitating the discovery of upcoming intriguing events within Event-Based Social Networks (EBSNs). Previous research has established the crucial significance of mining contextual features and implicit relationships to enhance recommendation performance and alleviate data sparsity issues. However, the noise inherent in contextual features exacerbates data sparsity and hampers the ability of previous methods to explore implicit relationships for mitigating data sparsity. To address this challenge, we propose a variational type graph autoencoder model that attenuates the influence of noise in different types of context features by introducing type-specific latent variables. First, we introduce a heterogeneous denoising convolution module composed of two components: (1) Denoising attention aggregation is proposed to mitigate the influence of noisy structures and uncover implicit relationships. (2) A heterogeneous normalization module leverages context features within the same type to alleviate the effects of noise in context features and data sparsity. Furthermore, we propose a learnable heterogeneous mixture prior that assists in assigning different priors to distinct types of latent variables, effectively modeling different types of contextual features. Through comprehensive experiments conducted on real-world datasets, we demonstrate the compelling performance of our model compared to state-of-the-art competitive approaches.

关键词： Event-based social networks Event recommendation Data sparsity Heterogeneous Information graph variational autoencoder Denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：