检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Ding, Shaojin Gutierrez-Osuna, Ricardo Texas A&M Univ Dept Comp Sci & Engn College Stn TX 77843 USA

This paper proposes a Group Latent Embedding for Vector Quantized variational autoencoders (VQ-VAE) used in non-parallel Voice Conversion (VC). Previous studies have shown that VQ-VAE can generate high-quality VC syntheses when it is paired with a powerful decoder. However, in a conventional VQ-VAE, adjacent atoms in the embedding dictionary can represent entirely different phonetic content. Therefore, the VC syntheses can have mispronunciations and distortions whenever the output of the encoder is quantized to an atom representing entirely different phonetic content. To address this issue, we propose an approach that divides the embedding dictionary into groups and uses the weighted average of atoms in the nearest group as the latent embedding. We conducted both objective and subjective experiments on the non-parallel CSTR VCTK corpus. Results show that the proposed approach significantly improves the acoustic quality of the VC syntheses compared to the traditional VQ-VAE (13.7% relative improvement) while retaining the voice identity of the target speaker.

关键词： non-parallel voice conversion variational autoencoder group latent embedding

来源：评论

学校读者我要写书评

暂无评论

Efficiency of Reinforcement Learning using Polarized Regime by variational autoencoder 61

Efficiency of Reinforcement Learning using Polarized Regime ...

引用

61st Annual Conference of the Society-of-Instrument-and-Control-Engineers (SICE)

作者： Nakai, Masato Shibuya, Takeshi Univ Tsukuba Doctoral Program Intelligent & Mech Interact Syst Tsukuba Japan Univ Tsukuba Fac Engn Informat & Syst Tsukuba Japan

ISBN: (数字)9784907764784

ISBN: (纸本)9784907764784

Reinforcement learning from low-dimensional state expressions extracted as features from images is more efficient than learning directly from high-dimensional images. The autoencoder (AE) is typically used to render an image into a low-dimensional state;reinforcement learning on latent variables encoded by variational autoencoder (VAE) give excellent results. Notably, VAE is known to have a polarized regime and disentanglement among the generated latent variables. However very few studies have attempted to improve the efficiency of reinforcement learning using a polarized regime. This paper demonstrates the capability of a VAE polarized regime to improve the efficiency of reinforcement learning using an interactive driving game. It was found that only some polarized latent variables contribute to image restoration and reinforcement learning. The results show that calculation times can be significantly shortened while maintaining performance by reducing the number of search points of ES (Evolution Strategy) via the selection of only the latent variables that contribute to reinforcement learning using the polarized regime.

关键词： variational autoencoder polarized regime reinforcement learning state representation latent space evolution strategy

来源：评论

学校读者我要写书评

暂无评论

Data augmentation using a variational autoencoder for estimating property prices

引用

PROPERTY MANAGEMENT 2021年第3期39卷 408-418页

作者： Lee, Changro Kangwon Natl Univ Chunchon South Korea

Purpose Prior studies on the application of deep-learning techniques have focused on enhancing computation algorithms. However, the amount of data is also a key element when attempting to achieve a goal using a quantitative approach, which is often underestimated in practice. The problem of sparse sales data is well known in the valuation of commercial properties. This study aims to expand the limited data available to exploit the capability inherent in deep learning techniques. Design/methodology/approach The deep learning approach is used. Seoul, the capital of South Korea is selected as a case study area. Second, data augmentation is performed for properties with low trade volume in the market using a variational autoencoder (VAE), which is a generative deep learning technique. Third, the generated samples are added into the original dataset of commercial properties to alleviate data insufficiency. Finally, the accuracy of the price estimation is analyzed for the original and augmented datasets to assess the model performance. Findings The results using the sales datasets of commercial properties in Seoul, South Korea as a case study show that the augmented dataset by a VAE consistently shows higher accuracy of price estimation for all 30 trials, and the capabilities inherent in deep learning techniques can be fully exploited, promoting the rapid adoption of artificial intelligence skills in the real estate industry. Originality/value Although deep learning-based algorithms are gaining popularity, they are likely to show limited performance when data are insufficient. This study suggests an alternative approach to overcome the lack of data problem in property valuation.

关键词： Deep learning Data augmentation variational autoencoder Property valuation

来源：评论

学校读者我要写书评

暂无评论

Time Series Forecasting Based on Structured Decomposition and variational autoencoder

Time Series Forecasting Based on Structured Decomposition an...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhang, Zhiyuan Yao, Xuhui Civil Aviat Univ China Coll Comp Sci & Technol Tianjin Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Time series forecasting based on decomposition method usually decomposes a complex time series into some simple components, such as long-term and seasonal trends, which are more easy to be predicted. Though long-term and seasonal trends are vital in time series foreasting, it may be insufficient for those not having such obvious characters. This paper proposes a time series forecasting model named SD-VAE based on structured decomposition and variational autoencoder(VAE). The structured decomposition module decomposes a time series into long-term component, seasonal component, short-term component and co-evolving component, and the VAE module learns the representation of them, through which the future value of each decomposed component are predicted and then fused by a neural network. To get a better decoupled representation of each decomposed component, mutual information constraints are added in the latent space of VAE. Extensive experiments prove that our model performs the best in 3 out of 4 public datasets, with the other one ranking second, against the most representation learning and end-to-end forecasting models.

关键词： structured decomposition variational autoencoder time series forecasting decoupling mutual information

来源：评论

学校读者我要写书评

暂无评论

Jointly Trained variational autoencoder for Multi-Modal Sensor Fusion 22

Jointly Trained Variational Autoencoder for Multi-Modal Sens...

引用

22nd International Conference on Information Fusion (FUSION)

作者： Korthals, Timo Hesse, Marc Leitner, Juergen Melnik, Andrew Rueckert, Ulrich Bielefeld Univ Cognitron & Sensor Syst Bielefeld Germany Queensland Univ Technol Australian Ctr Robot Vis Brisbane Qld Australia Bielefeld Univ Neuroinformat Grp Bielefeld Germany

ISBN: (纸本)9780996452786

This work presents the novel multi-modal variational autoencoder approach M(2)VAE which is derived from the complete marginal joint log-likelihood. This allows the end-to-end training of Bayesian information fusion on raw data for all subsets of a sensor setup. Furthermore, we introduce the concept of in-place fusion applicable to distributed sensing where latent embeddings of observations need to be fused with new data. To facilitate in-place fusion even on raw data, we introduced the concept of a re-encoding loss that stabilizes the decoding and makes visualization of latent statistics possible. We also show that the M(2)VAE finds a coherent latent embedding, such that a single nave Bayes classifier performs equally well on all permutations of a bi-modal Mixture-of-Gaussians signal. Finally, we show that our approach outperforms current VAE approaches on a bi-modal MNIST & fashion-MNIST data set and works sufficiently well as a preprocessing on a tri-modal simulated camera & LiDAR data set from the Gazebo simulator.

关键词： Multi-Modal Fusion Deep Generative Model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Using a variational autoencoder to Learn Valid Search Spaces of Safely Monitored Autonomous Robots for Last-Mile Delivery 23

Using a Variational Autoencoder to Learn Valid Search Spaces...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Bentley, Peter J. Lim, Soo Ling Arcaini, Paolo Ishikawa, Fuyuki UCL Dept Comp Sci Autodesk Res London England UCL London Dept Comp Sci London England Natl Inst Informat Tokyo Japan

ISBN: (纸本)9798400701191

The use of autonomous robots for delivery of goods to customers is an exciting new way to provide a reliable and sustainable service. However, in the real world, autonomous robots still require human supervision for safety reasons. We tackle the realworld problem of optimizing autonomous robot timings to maximize deliveries, while ensuring that there are never too many robots running simultaneously so that they can be monitored safely. We assess the use of a recent hybrid machine-learningoptimization approach COIL (constrained optimization in learned latent space) and compare it with a baseline genetic algorithm for the purposes of exploring variations of this problem. We also investigate new methods for improving the speed and efficiency of COIL. We show that only COIL can find valid solutions where appropriate numbers of robots run simultaneously for all problem variations tested. We also show that when COIL has learned its latent representation, it can optimize 10% faster than the GA, making it a good choice for daily re-optimization of robots where delivery requests for each day are allocated to robots while maintaining safe numbers of robots running at once.

关键词： variational autoencoder autonomous robots scheduling learning latent representations genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning Community Structure with variational autoencoder 18

Learning Community Structure with Variational Autoencoder

引用

18th IEEE International Conference on Data Mining Workshops (ICDMW)

作者： Choong, Jun Jin Liu, Xin Murata, Tsuyoshi Tokyo Inst Technol Dept Comp Sci Tokyo Japan Natl Inst Adv Ind Sci & Technol Tokyo Japan

ISBN: (纸本)9781538691595

Discovering community structure in networks remains a fundamentally challenging task. From scientific domains such as biology, chemistry and physics to social networks the challenge of identifying community structures in different kinds of network is challenging since there is no universal definition of community structure. Furthermore, with the surge of social networks, content information has played a pivotal role in defining community structure, demanding techniques beyond its traditional approach. Recently, network representation learning have shown tremendous promise. Leveraging on recent advances in deep learning, one can exploit deep learning's superiority to a network problem. Most predominantly, successes in supervised and semi-supervised task has shown promising results in network representation learning tasks such as link prediction and graph classification. However, much has yet to be explored in the literature of community detection which is an unsupervised learning task. This paper proposes a deep generative model for community detection and network generation. Empowered with Bayesian deep learning, deep generative models are capable of exploiting non-linearities while giving insights in terms of uncertainty. Hence, this paper proposes variational Graph autoencoder for Community Detection (VGAECD). Extensive experiment shows that it is capable of outperforming existing state-of-the-art methods. The generalization of the proposed model also allows the model to be considered as a graph generator. Additionally, unlike traditional methods, the proposed model does not require a predefined community structure definition. Instead, it assumes the existence of latent similarity between nodes and allows the model to find these similarities through an automatic model selection process. Optionally, it is capable of exploiting feature-rich information of a network such as node content, further increasing its performance.

关键词： community detection variational autoencoder generative model

来源：评论

学校读者我要写书评

暂无评论

Device Image-IV Mapping using variational autoencoder for Inverse Design and Forward Prediction

Device Image-IV Mapping using Variational Autoencoder for In...

引用

International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)

作者： Lu, Thomas Lu, Albert Wong, Hiu Yung San Jose State Univ M PAC Lab San Jose CA 95192 USA

ISBN: (纸本)9784863488038

This paper demonstrates the learning of the underlying device physics by mapping device structure images to their corresponding Current-Voltage (IV) characteristics using a novel framework based on variational autoencoders (VAE). Since VAE is used, domain expertise is not required and the framework can be quickly deployed on any new device and measurement. This is expected to be useful in the compact modeling of novel devices when only device cross-sectional images and electrical characteristics are available (e.g. novel emerging memory). Technology Computer-Aided Design (TCAD) generated and hand-drawn Metal-OxideSemiconductor (MOS) device images and noisy drain-currentgate-voltage curves (IDVG) are used for the demonstration. The framework is formed by stacking two VAEs (one for image manifold learning and one for IDVG manifold learning) which communicate with each other through the latent variables. Five independent variables with different strengths are used. It is shown that it can perform inverse design (generate a design structure for a given IDVG) and forward prediction (predict IDVG for a given structure image, which can be used for compact modeling if the image is treated as device parameters) successfully. Since manifold learning is used, the machine is shown to be robust against noise in the inputs (i.e. using hand-drawn images and noisy IDVG curves) and not confused by weak and irrelevant independent variables.

关键词： Compact Modeling Inverse Design Machine Learning Manifold Learning Technology Computer-Aided Design (TCAD) variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

CONTINUAL LEARNING FOR ANOMALY DETECTION WITH variational autoencoder 44

CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AU...

引用

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

作者： Wiewel, Felix Yang, Bin Univ Stuttgart Inst Signal Proc & Syst Theory Stuttgart Germany

ISBN: (纸本)9781479981311

Detecting anomalies using a variational autoencoder (VAE) suffers from catastrophic forgetting when trained on a continually growing set of normal data where only the most recently added data is available. Solving this problem would allow the use of the VAE for anomaly detection in settings where it is difficult or even impossible to retain all normal data at the same time. We propose an efficient extension of a method for continual learning which alleviates catastrophic forgetting for anomaly detection using a VAE. We show on some anomaly detection problems that the definition of normal data can be continually expanded without requiring all previously seen data.

关键词： Continual Learning Anomaly Detection variational autoencoder Generative Replay

来源：评论

学校读者我要写书评

暂无评论

Improved variational autoencoder Anomaly Detection in Time Series Data

Improved Variational Autoencoder Anomaly Detection in Time S...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Yokkampon, Umaporn Chumkamon, Sakmongkon Mowshowitz, Abbe Fujisawa, Ryusuke Hayashi, Eiji Kyushu Inst Technol Dept Comp Sci & Syst Engn Fukuoka Japan CUNY City Coll Dept Comp Sci New York NY USA

ISBN: (纸本)9781728185262

Uncertainty in observations about the state of affairs is unavoidable, and generally undesirable, so we are motivated to try to minimize its effect on data analysis. Detection of anomalies in data has become an important research area. In this paper, we propose a novel approach to anomaly detection based on the variational autoencoder method with a Mish activation function and a Negative Log-Likelihood loss function. The proposed method is validated with ten standard datasets, comparing performance on each of the various activation functions and loss functions. Experimental results show that our proposed method offers an improvement over existing methods. Statistical properties (i.e., F1 score, AUC, and ROC) of the method are also examined in light of the experimental results.

关键词： Anomaly Detection variational autoencoder Time Series Data Activation Functions Loss Functions

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：