检索结果-内蒙古大学图书馆

Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2022年第7-9期90卷 735-752页

作者： Park, Seonho Adosoglou, George Pardalos, Panos M. Univ Florida Dept Ind & Syst Engn Gainesville FL 32611 USA

Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error of variational autoencoder (VAE) by maximizing the evidence lower bound. We revisit VAE from the perspective of information theory to provide some theoretical foundations on using the reconstruction error and finally arrive at a simpler yet effective model for anomaly detection. In addition, to enhance the effectiveness of detecting anomalies, we incorporate a practical model uncertainty measure into the anomaly score. We show empirically the competitive performance of our approach on benchmark data sets.

关键词： Anomaly detection Rate-Distortion theory Information theory Model uncertainty MC dropout variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder-based topological optimization of an anechoic coating: An efficient- and neural network-based design

引用

MATERIALS TODAY COMMUNICATIONS 2022年 32卷

作者： Sun, Yiping Li, Zhaoyu Chen, Jiadui Zhao, Xuefeng Tao, Meng Guizhou Univ Sch Mech Engn Guiyang 550025 Peoples R China Guizhou Open Univ Coll Aeronaut Guiyang 550023 Peoples R China Guizhou Univ Key Lab Adv Mfg Technol Minist Educ Guiyang 550025 Peoples R China

An anechoic coating is an artificial heterogeneous composite material composed of periodic cells with cavities. Using the local resonance of cavities to reduce their sound absorption frequencies and widen their frequency bands has been a research hotspot in recent years. One of the main challenges involves optimizing the cavity structure of an anechoic coating to obtain low-frequency, broadband, and strong sound absorption properties. In this paper, a variational autoencoder (VAE) model-based topology optimization method was investigated. First, the finite-element method (FEM) was used to calculate the sound absorption coefficient, and a dataset was constructed with samples whose average sound absorption coefficients ranged from 200 to 6000 Hz and were greater than 0.75. Then, the VAE model was trained to learn the key features of an anechoic coating. Finally, the data were reconstructed with Gaussian distributions. The decoder network of the trained VAE model was used to design a new anechoic coating. It took only approximately 3 s to generate 100 new topologies, and the average absorption coefficients were all greater than 0.754. This efficient neural network-based method can be further generalized to optimize the designs of various mechanical structural materials with specific functions.

关键词： Anechoic coating Topology optimization variational autoencoder Neural network

来源：评论

学校读者我要写书评

暂无评论

Curiosity-Driven variational autoencoder for Deep Q Network 24th

Curiosity-Driven Variational Autoencoder for Deep Q Network

引用

24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Han, Gao-Jie Zhang, Xiao-Fang Wang, Hao Mao, Chen-Guang Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9783030474263;9783030474256

In recent years, deep reinforcement learning (DRL) has achieved tremendous success in high-dimensional and large-scale space control and sequential decision-making tasks. However, the current model-free DRL methods suffer from low sample efficiency, which is a bottleneck that limits their performance. To alleviate this problem, some researchers used the generative model for modeling the environment. But the generative model may become inaccurate or even collapse if the state has not been sufficiently explored. In this paper, we introduce a model called Curiosity-driven variational autoencoder (CVAE), which combines variational autoencoder and curiosity-driven exploration. During the training process, the CVAE model can improve sample efficiency while curiosity-driven exploration can make sufficient exploration in a complex environment. Then, a CVAE-based algorithm is proposed, namely DQN-CVAE, that scales CVAE to higher dimensional environments. Finally, the performance of our algorithm is evaluated through several Atari 2600 games, and the experimental results show that the DQN-CVAE achieves better performance in terms of average reward per episode on these games.

关键词： Reinforcement learning Deep Q learning Exploration variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

CNC Machining Quality Prediction Using variational autoencoder: A Novel Industrial 2 TB Dataset

CNC Machining Quality Prediction Using Variational Autoencod...

引用

Prognostics and Health Management Conference (PHM-2022 London)

作者： Proteau, Antoine Zemouri, Ryad Tahan, Antoine Thomas, Marc Bounouara, Wafa Agnard, Stephane Ecole Technol Super Dept Mech Engn Montreal PQ Canada Conservatoire Natl Arts & Metiers CNAM CEDRIC Lab Paris France APN Inc Quebec City PQ Canada

ISBN: (纸本)9781665479547

The purpose of this paper is to present and to describe a novel dataset acquired entirely in an industrial environment during multiple regular scheduled production runs. In the monitoring, prognostic and fault detection literature, researchers are often faced with work based on the same popular datasets;for instance, the milling dataset, the Pronostia Bearing Dataset, the IMS Bearing Dataset or the Turbofan Engine Degradation Simulation Dataset. On the one hand, these datasets are the results of either simulations or acquired in a laboratory under controlled environment. On the other hand, a real industrial context might not be adequately represented within these datasets due to less controlled parameters or increased complexity. Consequently, it becomes critical to have access to a way to test and validate research work on both experimental and industrial data. In that mindset, to accelerate the technological transfer to the industry and to ensure that it can quickly profit from the benefits that the monitoring, diagnostic and prognostic research area can provide them, a new dataset acquired at an industrial partner: a machining company located in Quebec City (Qc, Canada) is presented.

关键词： Dataset Machining GD&T Prognostic variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks using variational autoencoder discrimination for super-resolution 6

Generative adversarial networks using variational autoencode...

引用

6th International Conference on Natural Language Processing (ICNLP)

作者： Xu, Jian Ren, Xiangbo Niu, Lijiao Guo, Jiayao Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian Peoples R China

ISBN: (纸本)9798350349122;9798350349115

Training generative adversarial networks (GANs) relies on the game between the generator and the discriminator, so the improvement of the discriminator can promote the improvement of the generator. A variational autoencoder (VAE) is useful for classification because it can learn the probability distribution of an image and provide latent variables as output features. Therefore, we propose a new network structure using a variational autoencoder in the GAN discriminator for super-resolution (SR). This network uses the latent variables generated by the VAE to extract the probability distribution of a reconstructed image and an original high-resolution (HR) image so the latent variables are used as features for discrimination. In addition, we propose to train the whole GAN and the VAE network alternately to optimize the network parameters. We verify the proposed method on five GAN-based image super-resolution methods. Experimental results show that the proposed algorithm leads to state-of-the-art results when plugged into existing GAN based SR methods.

关键词： Generative Adversarial Networks variational autoencoder Image Super-Resolution Algorithm

来源：评论

学校读者我要写书评

暂无评论

The Dreaming variational autoencoder for Reinforcement Learning Environments 38th

The Dreaming Variational Autoencoder for Reinforcement Learn...

引用

38th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence (AI)

作者： Andersen, Per-Arne Goodwin, Morten Granmo, Ole-Christoffer Univ Agder Dept ICT Grimstad Norway

ISBN: (纸本)9783030041915;9783030041908

Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms that prevent them from converging towards the global optima. It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms. Games are often used to benchmark reinforcement learning algorithms as they provide a flexible, reproducible, and easy to control environment. Regardless, few games feature a state-space where results in exploration, memory, and planning are easily perceived. This paper presents The Dreaming variational autoencoder (DVAE), a neural network based generative modeling architecture for exploration in environments with sparse feedback. We further present Deep Maze, a novel and flexible maze engine that challenges DVAE in partial and fully-observable state-spaces, long-horizon tasks, and deterministic and stochastic problems. We show initial findings and encourage further work in reinforcement learning driven by generative exploration.

关键词： Deep reinforcement learning Environment modeling Neural networks variational autoencoder Markov decision processes Exploration Artificial experience-replay

来源：评论

学校读者我要写书评

暂无评论

One-Class Collaborative Filtering with the Queryable variational autoencoder 19

One-Class Collaborative Filtering with the Queryable Variati...

引用

42nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Wu, Ga Bouadjenek, Mohamed Reda Sanner, Scott Univ Toronto Toronto ON Canada Vector Inst Artificial Intelligence Toronto ON Canada

ISBN: (纸本)9781450361729

variational autoencoder (VAE) based methods for Collaborative Filtering (CF) demonstrate remarkable performance for one-class (implicit negative) recommendation tasks by extending autoencoders with relaxed but tractable latent distributions. Explicitly modeling a latent distribution over user preferences allows VAEs to learn user and item representations that not only reproduce observed interactions, but also generalize them by leveraging learning from similar users and items. Unfortunately, VAE-CF can exhibit suboptimal learning properties;e.g., VAE-CFs will increase their prediction confidence as they receive more preferences per user, even when those preferences may vary widely and create ambiguity in the user representation. To address this issue, we propose a novel Queryable variational autoencoder (Q-VAE) variant of the VAE that explicitly models arbitrary conditional relationships between observations. The proposed model appropriately increases uncertainty (rather than reduces it) in cases where a large number of user preferences may lead to an ambiguous user representation. Our experiments on two benchmark datasets show that the Q-VAE generally performs comparably or outperforms VAE-based recommenders as well as other state-of-the-art approaches and is generally competitive across the user preference density spectrum, where other methods peak for certain preference density levels.

关键词： One-Class Collaborative Filtering variational autoencoder Conditional Inference

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 133卷

作者： Wang, Ziyuan Wang, Chengzhu Li, Yonggang Cent South Univ Sch Automat Changsha 410083 Peoples R China China Tobacco Hunan Ind Co Ltd Changsha Cigarette Factory Changsha 410034 Peoples R China

The severity of faults and the corresponding solutions in the complex and large-scale modern manufacturing industry are determined based on their impact on product quality. Detecting faults that affect product quality is crucial for minimizing downtime and reducing maintenance costs. However, obtaining real-time indicators of product quality is often challenging. Therefore, in practical production settings, it becomes essential to develop methods for detecting process -quality faults without relying on real-time quality data. Existing processquality concurrent fault detection methods establish process -variable -quality -variable relationships to design monitoring statistics. variational autoencoder (VAE) is extensively utilized to disentangle quality -related information from quality -unrelated information by ensuring the independence of the extracted features. However, the current VAE-based model structures lack theoretical support from probability models, and the feature extraction solely from process variables may not fully capture quality indicators. Therefore, we propose a novel VAE based on knowledge sharing and correlation weighting (KSCW-VAE) with theoretical interpretability to realize process -quality concurrent fault detection. First, to extract information from quality variables, a novel VAE model with two input branches is constructed. The EncoderNet branch includes both process variables and quality variables, while the PriorNet branch comprises only process variables. Then, Kullback- Leibler (KL) divergence constraint is introduced to facilitate effective extraction of combined information from process variables and quality variables by leveraging knowledge sharing between EncoderNet and PriorNet. To differentiate quality -related and quality -unrelated information, separate regression networks for process variables and quality variables are constructed by segregating latent variables. In addition, a network weight regularization based on canonical c

关键词： Fault detection Process-quality concurrent variational autoencoder Knowledge sharing Zinc roaster

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder-Based Multiobjective Topology Optimization of Electrical Machines Using Vector Graphics

引用

IEEE ACCESS 2024年 12卷 184813-184826页

作者： Heroth, Michael Schmid, Helmut C. Gregorova, Magda Herrler, Rainer Hofmann, Wilfried ZF Friedrichshafen AG Adv Dev E Motor Simulat D-88046 Schweinfurt Germany TH Wurzburg Schweinfurt CAIRO D-97421 Wurzburg Germany Tech Univ Dresden Chair Elect Machines & Drives D-01069 Dresden Germany

The increasing automation in the design process of electrical machines for vehicles generates huge amounts of data, leading to a growing interest in using machine learning for faster predictions and optimization. This paper presents an innovative approach to simultaneously model and optimize different geometries of electrical machines. Unlike previous methods that rely on specific design variables or pixel-based representations, this approach is based on a flexible vector graphic representation that can easily be applied to any electrical machine configuration. This also sidesteps the problem of scalar-based design representation and, unlike pixel-based representation, can be directly imported into finite element simulations for validation. To speed up the optimization process, we transform the corresponding problem into a lower-dimensional latent space learned by a variational autoencoder. This is trained on a total of 6839 different 2D geometries of electrical machines, which were exported from the finite element simulation into the standardized scalable vector graphics format. The optimization results show that a sharp boundary is formed in the combined Pareto front of different rotor topologies. The validation results demonstrate that this novel method delivers results comparable to those of current techniques.

关键词： Geometry Optimization Topology Graphics Vectors Training data Rotors Training Databases Synchronous machines Deep neural network multiobjective optimization permanent magnet synchronous machine scalable vector graphics variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Evaluating variational autoencoder as a Private Data Release Mechanism for Tabular Data 24

Evaluating Variational Autoencoder as a Private Data Release...

引用

IEEE 24th Pacific Rim International Symposium on Dependable Computing (PRDC)

作者： Li, Szu-Chuang Tai, Bo-Chen Huang, Yennun Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan

ISBN: (纸本)9781728149615

Multi-market businesses can collect data from different business entities and aggregate data from various sources to create value. However, due to the restriction of privacy regulation, it could be illegal to exchange data between business entities of the same parent company, unless the users have opted-in to allow it. Regulations such as the EU's GDPR allows data exchange if data is anonymized appropriately. In this study, we use variational autoencoder as a mechanism to generate synthetic data. The privacy and utility of the generated data sets are measured. And its performance is compared with the performance of the plain autoencoder. The primary findings of this study are 1) variational autoencoder can be an option for data exchange with good accuracy even when the number of latent dimensions is low 2) plain autoencoder still provides better accuracy when the number of hidden nodes is high 3) variational autoencoder, as a generative model, can be given to a data user to generate his version of data that closely mimic the original data set.

关键词： variational autoencoder private data release k-anonymity k-Level

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：