检索结果-内蒙古大学图书馆

Deep generative models in inversion: The impact of the generator's nonlinearity and development of a new approach based on a variational autoencoder

引用

COMPUTERS & GEOSCIENCES 2021年 152卷 104762-104762页

作者： Lopez-Alvis, Jorge Laloy, Eric Nguyen, Frederic Hermans, Thomas Univ Liege Urban & Environm Engn Appl Geophys Liege Belgium Univ Ghent Dept Geol Ghent Belgium Belgian Nucl Res Ctr Inst Environm Hlth & Safety Engn & Geosyst Anal Mol Belgium

When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological setting) of the subsurface. In such case, inversion may be formulated in a latent space where a lowdimensional parameterization of the patterns is defined and where Markov chain Monte Carlo or gradient-based methods may be applied. However, the generative mapping between the latent and the original (pixel) representations is usually highly nonlinear which may cause some difficulties for inversion, especially for gradientbased methods. In this contribution we review the conceptual framework of inversion with DGMs and propose that this nonlinearity is caused mainly by changes in topology and curvature induced by the generative function. As a result, we identify a conflict between two goals: the accuracy of the generated patterns and the feasibility of gradient-based inversion. In addition, we show how some of the training parameters of a variational autoencoder, which is a particular instance of a DGM, may be chosen so that a tradeoff between these two goals is achieved and acceptable inversion results are obtained with a stochastic gradient-descent scheme. A series of test cases using synthetic models with channel patterns of different complexity and cross-borehole traveltime tomographic data involving both a linear and a nonlinear forward operator show that the proposed method provides useful results and performs better compared to previous approaches using DGMs with gradient-based inversion.

关键词： Deep generative model Geophysical inversion Geological prior information variational autoencoder Stochastic gradient descent Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Semi-supervised variational autoencoder with Gate Mechanism for Text Classification

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2022年第10期36卷 2253006-2253006页

作者： Ye, Haiming Zhang, Weiwen Nie, Mengna Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China

In recent years, semi-supervised learning has been investigated to take full advantages of increasing unlabeled data. Although pretrained deep learning models are successfully adopted on a massive amount of unlabeled data, they may not be applicable in specific domains as the data is limited. In this paper, we propose a model, termed Semi-supervised variational autoencoder (SVAE), which consists of Gated Convolutional Neural Networks (GCNN) as both the encoder and the decoder. Since the canonical VAE suffers from Kullback-Leibler (KL) vanishing problem, we attach a layer named Scalar after Batch Normalization (BN) to scale the output of the BN. We conduct experiments on two domain-specific datasets with a small amount of data. The results show that SVAE outperforms other alternative baselines for language modeling and semi-supervised learning studies. Especially, the results in the language modeling validate the effect of combining BN and Scalar for tackling the KL vanishing problem. Moreover, the visualization of the latent representations verifies the performance of SVAE on less data.

关键词： Semi-supervised learning variational autoencoder text classification gated convolutional neural networks Kullback-Leibler vanishing problem

来源：评论

学校读者我要写书评

暂无评论

A dimensionality reduction algorithm for mapping tokamak operational regimes using a variational autoencoder (VAE) neural network

引用

NUCLEAR FUSION 2021年第12期61卷 126063-126063页

作者： Wei, Y. Levesque, J. P. Hansen, C. J. Mauel, M. E. Navratil, G. A. Columbia Univ Dept Appl Phys & Appl Math New York NY 10027 USA Univ Washington Dept Aeronaut & Astronaut Seattle WA 98195 USA

A variational autoencoder (VAE) is a type of unsupervised neural network which is able to learn meaningful data representations in a reduced dimensional space. We present an application of VAE in identifying the operational stability boundary of tokamak plasma discharges. This model was implemented using a dataset of over 3000 discharges from the high beta tokamak-extended pulse (HBT-EP) device. We found the VAE model to be capable of forming a continuous low-dimensional operational space map and identifying the operational boundaries using a specified warning time window. By projecting the operational parameters onto the same reduced space, this provides an intuitive way for the machine operator or an automated control system to perform disruption avoidance using a relevant control actuator as a discharge approaches a boundary. Pre-programmed GPU control experiments were conducted to demonstrate this control technique using HBT-EP's saddle control coils as a horizontal position actuator, showing the ability to avoid the oncoming disruptive event and extend the duration of the discharge.

关键词： disruption avoidance machine learning neural network variational autoencoder HBT-EP feedback control

来源：评论

学校读者我要写书评

暂无评论

Reconstructing a quantum state with a variational autoencoder

引用

INTERNATIONAL JOURNAL OF QUANTUM INFORMATION 2021年第8期19卷 2140005-2140005页

作者： Chen, Chuangtao He, Zhimin Huang, Zhiming Situ, Haozhen Foshan Univ Sch Elect & Informat Engn 33 Guangyun Rd Foshan 528225 Guangdong Peoples R China Wuyi Univ Sch Econ & Management 22 Dongcheng Village Jiangmen 529020 Guangdong Peoples R China South China Agr Univ Coll Math & Informat 483 Wushan Rd Guangzhou 510642 Guangdong Peoples R China

Quantum state tomography (QST) is an important and challenging task in the field of quantum information, which has attracted a lot of attentions in recent years. Machine learning models can provide a classical representation of the quantum state after trained on the measurement outcomes, which are part of effective techniques to solve QST problem. In this work, we use a variational autoencoder (VAE) to learn the measurement distribution of two quantum states generated by MPS circuits. We first consider the Greenberger-Horne-Zeilinger (GHZ) state which can be generated by a simple MPS circuit. Simulation results show that a VAE can reconstruct 3- to 8-qubit GHZ states with a high fidelity, i.e., 0.99, and is robust to depolarizing noise. The minimum number (N-s(*)) of training samples required to reconstruct the GHZ state up to 0.99 fidelity scales approximately linearly with the number of qubits (N). However, for the quantum state generated by a complex MPS circuit, N-s(*) increases exponentially with N, especially for the quantum state with high entanglement entropy.

关键词： Quantum state tomography quantum machine learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A variational autoencoder (VAE)-based Deep Learning Anomaly Detection Model for Industrial Products with Dynamic Weights Assigned to Loss Function

引用

SENSORS AND MATERIALS 2023年第7期35卷 2241-2264页

作者： Nakata, Shunta Kasahara, Takehiro Nambo, Hidetaka Kanazawa Univ Grad Sch Nat Sci & Technol Div Elect & Comp Sci Kanazawa Ishikawa 9201192 Japan Ind Res Inst Ishikawa Kanazawa Ishikawa 928203 Japan

In the industrial field, deep-learning-based image anomaly detections are attracting attention because of some of their advantages. The deep-learning-based models can overcome the shortcomings of traditional methods, such as human eye detection and rule-based machine detection. When using deep learning, which has many advantages, one of the limitations is that anomalous products are difficult to obtain. Since most industrial products do not have defects, unsupervised learning detection models are strongly required. We propose a new model based on the variational autoencoder ( VAE), which is a generative model applicable to detection by unsupervised learning. VAE is a model for optimizing parameters or latency based on a loss function that is the sum of several terms, and in our proposed method, original weights are given to these terms. In addition, our model dynamically and adaptively explores a ratio of weights. We have developed a dynamic weighted VAE adapted to area under the receiver operating characteristic curve (AUROC, AUC) using validation data. We have already reported the efficiency of the AUC-adapted VAE;however, this method is not unsupervised learning, and a method that does not use validation data was desired. In this paper, we discuss the previous method in more detail and describe the new method, which is fully unsupervised learning, by conducting additional experiments. The results of several experiments show that the proposed method is potentially effective for some actual industrial product image datasets while maintaining unsupervised learning.

关键词： anomaly detection industrial product variational autoencoder deep learning generative model loss function unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

PuVAE: A variational autoencoder to Purify Adversarial Examples

引用

IEEE ACCESS 2019年 7卷 126582-126593页

作者： Hwang, Uiwon Park, Jaewoo Jang, Hyemi Yoon, Sungroh Cho, Nam Ik Seoul Natl Univ Elect & Comp Engn Seoul 08826 South Korea Seoul Natl Univ INMC Dept Elect & Comp Engn Seoul 08826 South Korea

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise networks at inference time by applying elaborately designed perturbations to input data. Although several defense methods have been proposed to address specific attacks, other types of attacks can circumvent these defense mechanisms. Therefore, we propose Purifying variational autoencoder (PuVAE), a method to purify adversarial examples. The proposed method eliminates an adversarial perturbation by projecting an adversarial example on the manifold of each class and determining the closest projection as a purified sample. We experimentally illustrate the robustness of PuVAE against various attack methods without any prior knowledge about the attacks. In our experiments, the proposed method exhibits performances that are competitive with state-of-the-art defense methods, and the inference time is approximately 130 times faster than that of Defense-GAN which is a state-of-the art purifier method.

关键词： Adversarial attack variational autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

A mutual information-based variational autoencoder for robust JIT soft sensing with abnormal observations

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2020年 204卷 104118-104118页

作者： Guo, Fan Huang, Biao Univ Alberta Dept Chem & Mat Engn Edmonton AB T6G 2G6 Canada

Considering industrial process with high-dimensional, intrinsic nonlinearities and possibly abnormal observations, a robust deep learning soft sensor model is developed under the just-in-time learning framework. As an unsupervised deep learning approach, variational autoencoder (VAE) has been successfully applied to soft sensing problems owing to its ability to describe the latent representations by probability distributions. In this work, to construct high performance soft sensor model, mutual information (MI) is first introduced for input variable selection. By further incorporating MI as weights on variable of the traditional VAE model, a MI-based output-relevant VAE is developed. For each new sample that arrives, by utilizing Symmetric Kullback-Leibler (SKL) divergence, its relevance with historical samples is determined. Based on the SKL divergence, the input samples that are most relevant to the query sample can be collected. The selected historical input samples and corresponding output samples are employed to build a Gaussian process regression (GPR) local model. Expectation maximation (EM) algorithm is utilized to deal with the nonlinearity and abnormal output observations in GPR local model simultaneously for robustness of the soft sensors. Numerical simulations and a benchmark process are employed to validate the effectiveness of the proposed soft sensor, which demonstrates its superior performance over traditional approaches.

关键词： variational autoencoder Mutual information Just-in-time learning Outliers Missing data

来源：评论

学校读者我要写书评

暂无评论

Spatial-contextual variational autoencoder with attention correction for anomaly detection in retinal OCT images

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 152卷 106328-106328页

作者： Zhou, Xueying Niu, Sijie Li, Xiaohui Zhao, Hui Gao, Xizhan Liu, Tingting Dong, Jiwen Univ Jinan Sch Informat Sci & Engn Shandong Prov Key Lab Network Based Intelligent Co Jinan 250022 Shandong Peoples R China Shandong First Med Univ & Shandong Acad Med Sci Shandong Eye Hosp Shandong Eye Inst State Key Lab Cultivat BaseShandong Prov Key Lab Jinan 250022 Shandong Peoples R China

Anomaly detection refers to leveraging only normal data to train a model for identifying unseen abnormal cases, which is extensively studied in various fields. Most previous methods are based on reconstruction models, and use anomaly score calculated by the reconstruction error as the metric to tackle anomaly detection. However, these methods just employ single constraint on latent space to construct reconstruction model, resulting in limited performance in anomaly detection. To address this problem, we propose a Spatial- Contextual variational autoencoder with Attention Correction for anomaly detection in retinal OCT images. Specifically, we first propose a self-supervised segmentation network to extract retinal regions, which can effectively eliminate interference of background regions. Next, by introducing both multi-dimensional and one-dimensional latent space, our proposed framework can then learn the spatial and contextual manifolds of normal images, which is conducive to enlarging the difference between reconstruction errors of normal images and those of abnormal ones. Furthermore, an ablation-based method is proposed to localize anomalous regions by computing the importance of feature maps, which is used to correct anomaly score calculated by reconstruction error. Finally, a novel anomaly score is constructed to separate the abnormal images from the normal ones. Extensive experiments on two retinal OCT datasets are conducted to evaluate our proposed method, and the experimental results demonstrate the effectiveness of our approach.

关键词： Anomaly detection variational autoencoder Anomaly attention map Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Randomly generating three-dimensional realistic schistous sand particles using deep learning: variational autoencoder implementation

引用

ENGINEERING GEOLOGY 2021年 291卷 106235-106235页

作者： Shi, Jia-jie Zhang, Wei Wang, Wei Sun, Yun-han Xu, Chuan-yi Zhu, Hong-hu Sun, Zheng-xing Nanjing Univ Sch Earth Sci & Engn Nanjing 210023 Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Peoples R China

Nanjing sand, a type of greenish-grey schistous sand, is rich in weathered mica fragments, making it anisotropic and significantly differ from the round-grained quartz sand in terms of composition, grading, and mechanical properties. In this paper, the variational-autoencoder (VAE), a generative deep-learning model, was used to randomly generate realistic three-dimensional (3D) schistous sand particles. A training set was developed based on a micro-computed tomography scanned image sequence of the specimens of Nanjing sand. A total of 30,000 particles were chosen as the training set. Two thousand realistic 3D schistous sand particles were randomly generated by the trained VAE model and statistically compared with all the natural sand particles. The agreement of the statistical distribution and parameters between the generated and natural schistous sand particles confirmed the generative fidelity of the trained VAE model. Also, the validity and controllability of the generation is testified by the addition of Gaussian random noise and conducting linear interpolation to the latent variables. This methodology not only can be used for the clump template of the DEM, but also holds the potential of generating other geological entities and modeling complicated engineering geological processes.

关键词： Schistous sand Random particle generation Deep learning variational autoencoder Micro-computed tomography imaging Gaussian random noise

来源：评论

学校读者我要写书评

暂无评论

Diverse Image Captioning via Conditional variational autoencoder and Dual Contrastive Learning

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第1期20卷 29-29页

作者： Xu, Jing Liu, Bing Zhou, Yong Liu, Mingming Yao, Rui Shao, Zhiwen China Univ Min & Technol Sch Comp Sci & Technol Engn Res Ctr Mine Digitizat Minist Educ Xuzhou 221116 Jiangsu Peoples R China

Diverse image captioning has achieved substantial progress in recent years. However, the discriminability of generative models and the limitation of cross entropy loss are generally overlooked in the traditional diverse image captioning models, which seriously hurts both the diversity and accuracy of image captioning. In this article, aiming to improve diversity and accuracy simultaneously, we propose a novel Conditional variational autoencoder (DCL-CVAE) framework for diverse image captioning by seamlessly integrating sequential variational autoencoder with contrastive learning. In the encoding stage, we first build conditional variational autoencoders to separately learn the sequential latent spaces for a pair of captions. Then, we introduce contrastive learning in the sequential latent spaces to enhance the discriminability of latent representations for both image-caption pairs andmismatched pairs. In the decoding stage, we leverage the captions sampled from the pre-trained Long Short-Term Memory (LSTM), LSTM decoder as the negative examples and perform contrastive learning with the greedily sampled positive examples, which can restrain the generation of common words and phrases induced by the cross entropy loss. By virtue of dual constrastive learning, DCL-CVAE is capable of encouraging the discriminability and facilitating the diversity, while promoting the accuracy of the generated captions. Extensive experiments are conducted on the challenging MSCOCO dataset, showing that our proposed methods can achieve a better balance between accuracy and diversity compared to the state-of-the-art diverse image captioning models.

关键词： Diverse image captioning variational autoencoder contrastive learning sequential latent space

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：