Filters








2,738 Hits in 6.6 sec

Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection [article]

Erik Daxberger, José Miguel Hernández-Lobato
2020 arXiv   pre-print
We propose a new probabilistic, unsupervised approach to this problem based on a Bayesian variational autoencoder model, which estimates a full posterior distribution over the decoder parameters using  ...  While this has recently motivated the development of methods to detect such out-of-distribution (OoD) inputs, a robust solution is still lacking.  ...  Problem Statement and Background Out-of-Distribution (OoD) Detection For input space OoD detection, we are given a large set D = {x i } N i=1 of high-dimensional training inputs x i ∈ X (i.e., with N  ... 
arXiv:1912.05651v3 fatcat:crdv3vghorddxe2vv5uang6aze

Autoencoder based Semi-Supervised Anomaly Detection in Turbofan Engines

Ali Al Bataineh, Aakif Mairaj, Devinder Kaur
2020 International Journal of Advanced Computer Science and Applications  
This paper proposes a semi-supervised autoencoder based approach for the detection of anomalies in turbofan engines.  ...  Optimal architecture of autoencoder is discovered using Bayesian hyperparameter tuning approach.  ...  This issue of imbalance class distribution is addressed in [8] . Unsupervised anomaly detection algorithms do not require true labels of data instances for training.  ... 
doi:10.14569/ijacsa.2020.0111105 fatcat:qf56pf5egrghrbvmxcxjudtmoe

Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges [article]

Muhammad Usama, Junaid Qadir, Aunn Raza, Hunain Arif, Kok-Lim Alvin Yau, Yehia Elkhatib, Amir Hussain, Ala Al-Fuqaha
2017 arXiv   pre-print
detection, Internet traffic classification, and quality of service optimization.  ...  We provide a comprehensive survey highlighting the recent advancements in unsupervised learning techniques and describe their applications for various learning tasks in the context of networking.  ...  Variational autoencoder is an unsupervised learning technique used clustering, dimensionality reduction and visualization, and for learning complex distributions [40] .  ... 
arXiv:1709.06599v1 fatcat:llcg6gxgpjahha6bkhsitglrsm

Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges

Muhammad Usama, Junaid Qadir, Aunn Raza, Hunain Arif, Kok-lim Alvin Yau, Yehia Elkhatib, Amir Hussain, Ala Al-Fuqaha
2019 IEEE Access  
anomaly detection, Internet traffic classification, and quality of service optimization.  ...  In addition, unsupervised learning can unconstrain us from the need for labeled data and manual handcrafted feature engineering, thereby facilitating flexible, general, and automated methods of machine  ...  Variational autoencoder is an unsupervised learning technique used clustering, dimensionality reduction, and visualization, and for learning complex distributions [47] .  ... 
doi:10.1109/access.2019.2916648 fatcat:xutxh3neynh4bgcsmugxsclkna

Revisiting Bayesian Autoencoders with MCMC [article]

Rohitash Chandra, Mahir Jain, Manavendra Maharana, Pavel N. Krivitsky
2021 arXiv   pre-print
This motivates further application of the Bayesian autoencoder framework for other deep learning models.  ...  This has been addressed with variational autoencoders so far.  ...  CONCLUSIONS We presented a framework that employs tempered MCMC sampling for the Bayesian autoencoder which is an alternative to the variational autoencoder.  ... 
arXiv:2104.05915v1 fatcat:6gr6lxe2eja2ljsqrvyg3kpeii

Anomaly Detection in Industrial Software Systems - Using Variational Autoencoders

Tharindu Kumarage, Nadun De Silva, Malsha Ranawaka, Chamal Kuruppu, Surangika Ranathunga
2018 Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods  
This paper presents the application of a deep learning neural network known as Variational Autoencoder (VAE), as the solution to this problem.  ...  Nevertheless, the high complexity of the system components makes anomaly detection a high dimensional machine learning problem.  ...  ACKNOWLEDGEMENTS The authors thank MillenniumIT Software (Private) Ltd. for providing the datasets for industrial system evaluation.  ... 
doi:10.5220/0006600304400447 dblp:conf/icpram/KumarageSRKR18 fatcat:kvfm6f2uajd7nhklyglvgjrvpa

StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder [article]

Soumick Chatterjee, Alessandro Sciarra, Max Dünnwald, Pavan Tummala, Shubham Kumar Agrawal, Aishwarya Jauhari, Aman Kalra, Steffen Oeltze-Jafra, Oliver Speck, Andreas Nürnberger
2022 arXiv   pre-print
Hence, a possible solution is an unsupervised anomaly detection (UAD) system that can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out of distribution  ...  Several Variational Autoencoder (VAE) based techniques have been proposed in the past for this task.  ...  ZS/2016/08/80646) and was supported by the federal state of Saxony-Anhalt ("I 88").  ... 
arXiv:2201.13271v2 fatcat:uvvhr4ydnrejvngcwjkrv34zui

Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations

Jakub Jakubowski, Przemysław Stanisz, Szymon Bobek, Grzegorz J. Nalepa
2021 Sensors  
The results show that the variational autoencoder slightly outperforms the base autoencoder architecture in anomaly detection tasks.  ...  In the paper we present how unsupervised learning using a variational autoencoder may be used to monitor the wear of rolls in a hot strip mill, a part of a steel-making site.  ...  Anomaly Detection Using Variational Autoencoder with Explanations In this study, we have proposed a solution for unsupervised anomaly detection in an asset where a deep variational autoencoder is learned  ... 
doi:10.3390/s22010291 pmid:35009832 pmcid:PMC8749861 fatcat:c7pvxmofsvaeplisntm4csc7zi

Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder [article]

Ting-Yun Cheng, Nan Li, Christopher J. Conselice, Alfonso Aragón-Salamanca, Simon Dye, Robert B. Metcalf
2020 arXiv   pre-print
In this paper we develop a new unsupervised machine learning technique comprised of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian  ...  Additionally, our unsupervised clustering process can be used as the preliminary classification for future surveys of lenses to efficiently select targets and to speed up the labelling process.  ...  Ting-Yun Cheng gives a thank to the support of the Vice-Chancellor's Scholarship from the University of Nottingham, and discussions with Bobby Clement.  ... 
arXiv:1911.04320v2 fatcat:6mzk2sppqzexhfi2nwc55pisxu

Nonparametric Variational Auto-encoders for Hierarchical Representation Learning [article]

Prasoon Goyal, Zhiting Hu, Xiaodan Liang, Chenyu Wang, Eric Xing
2017 arXiv   pre-print
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods.  ...  In this work, we propose hierarchical nonparametric variational autoencoders, which combines tree-structured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation  ...  FA8702-15-D-0002 with Carnegie Mellon University for the operation of the Software Engineering Institute, a federally funded research and development center.  ... 
arXiv:1703.07027v2 fatcat:fllrzupobrfhjpjeejjgzgmve4

Categorization in Unsupervised Generative Selflearning Systems

Serge Dolgikh, Department of Information Technology, National Aviation University, Kyiv, Ukraine
2021 International Journal of Modern Education and Computer Science  
with Bayesian inference principle, favor configurations with better categorization of hidden concepts in the observable data.  ...  He has a number of publications in Theoretical Physics, Information Theory research and technology applications and has worked on industry projects with leading network technology providers for over 15  ...  Acknowledgment The authors wish to thank the colleagues at the Department of Information Technology, National Aviation University, and Network Engineering, Solana Networks for valuable discussions about  ... 
doi:10.5815/ijmecs.2021.03.06 fatcat:hu4porr63zbodnfwhutzkkvuhu

Revisiting Bayesian autoencoders with MCMC

Rohitash Chandra, Mahir Jain, Manavendra Maharana, Pavel N. Krivitsky
2022 IEEE Access  
This motivates further applications of the Bayesian autoencoder framework for other deep learning models.  ...  This has been addressed with variational autoencoders so far.  ...  CONCLUSION We presented a framework that employs tempered MCMC sampling for the Bayesian autoencoder which is an alternative to the variational autoencoder.  ... 
doi:10.1109/access.2022.3163270 fatcat:eibediyxyzc45hn6hyssbllxcy

Deep Gaussian Process autoencoders for novelty detection

Rémi Domingues, Pietro Michiardi, Jihane Zouaoui, Maurizio Filippone
2018 Machine Learning  
This paper proposes a novel autoencoder based on Deep Gaussian Processes for novelty detection tasks.  ...  Learning the proposed model is made tractable and scalable through the use of random feature approximations and stochastic variational inference.  ...  Acknowledgements The authors wish to thank the Amadeus Middleware Fraud Detection team directed by Virginie Amar and Jeremie Barlet, led by the product owner Christophe Allexandre and composed of Jean-Blas  ... 
doi:10.1007/s10994-018-5723-3 fatcat:3jbo73e5wfes7c2k5x4p6sycjq

Multidimensional Time Series Anomaly Detection: A GRU-based Gaussian Mixture Variational Autoencoder Approach

Yifan Guo, Weixian Liao, Qianlong Wang, Lixing Yu, Tianxi Ji, Pan Li
2018 Asian Conference on Machine Learning  
Some existing works use traditional variational autoencoder (VAE) for anomaly detection. They generally assume a single-modal Gaussian distribution as prior in the data generative procedure.  ...  Unsupervised anomaly detection on multidimensional time series data is a very important problem due to its wide applications in many systems such as cyber-physical systems, the Internet of Things.  ...  Variational Autoencoder based Anomaly Detection Variational autoencoder is a probabilistic model which combines bayesian inference with the autoenoder framework.  ... 
dblp:conf/acml/GuoLWYJL18 fatcat:uajem3wi5fcnxguunjzg6yhvbe

Decoding Dark Matter Substructure without Supervision [article]

Stephon Alexander, Sergei Gleyzer, Hanna Parul, Pranath Reddy, Michael W. Toomey, Emanuele Usai, Ryker Von Klar
2021 arXiv   pre-print
In this work we demonstrate the use of unsupervised machine learning techniques to infer the presence of substructure in dark matter halos using galaxy-galaxy strong lensing simulations.  ...  While it is possible that one of the many proposed candidates may turn out to be dark matter, it is at least equally likely that the correct physical description has yet to be proposed.  ...  ACKNOWLEDGEMENTS We would like to thank Evan McDonough and Ali Hariri for useful discussions. K Pranath Reddy is a participant in the Google Summer of Code (GSoC) 2020 program.  ... 
arXiv:2008.12731v2 fatcat:6tlot3wt2fctrnx6vrj2kwmu2u
« Previous Showing results 1 — 15 out of 2,738 results