Filters








27,659 Hits in 2.1 sec

The Infinite Latent Events Model [article]

David Wingate, Noah Goodman, Daniel Roy, Joshua Tenenbaum
2012 arXiv   pre-print
We present the Infinite Latent Events Model, a nonparametric hierarchical Bayesian distribution over infinite dimensional Dynamic Bayesian Networks with binary state representations and noisy-OR-like transitions  ...  The distribution can be used to learn structure in discrete timeseries data by simultaneously inferring a set of latent events, which events fired at each timestep, and how those events are causally linked  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments.  ... 
arXiv:1205.2604v1 fatcat:hgbmnhhmwrdtnf2izntnbfztgy

Tail-measurability in monotone latent variable models

Jules L. Ellis, Brian W. Junker
1997 Psychometrika  
We consider latent variable models for an infinite sequence (or universe) of manifest (observable) variables that may be discrete, continuous or some combination of these.  ...  These definitions do not require the a priori specification of a latent variable model.  ...  The subtail-measurable monotone L V model implies asymptotic specific objectivity of the ordinal comparison of persons: Whenever two infinite subsequences X i and Xj yield latent variables 0 i and ®j,  ... 
doi:10.1007/bf02294640 fatcat:swv3sex2jjfbbifqyzzzgeuku4

Infinite Latent Topic Models for Document Analysis
문서 분석을 위한 무한 잠재 주제 모형

Bong-Kee Sin
2018 Journal of KIISE  
This paper presents infinite topic extensions to the well-known model of Latent Dirichlet Allocation (LDA) i.e., the infinite Latent Dirichlet Topic model and the infinite Latent Markov Topic model.  ...  The first model simply relaxes the constraint of fixed known number of topics in LDA using the method of the Dirichlet process.  ...  The particular generative models we present, called Infinite Latent Topic Model and Infinite Latent Markov Topic Model, are developed here on top of the previous works [4,5] besides the famous Latent Dirichlet  ... 
doi:10.5626/jok.2018.45.7.701 fatcat:bjsseefvyre6fkvt7dhfyfewfu

Survey on Seizure Reports from Clandestine Labs

2016 International Journal of Science and Research (IJSR)  
This paper focus on extraction the information and then review the visualization tasks related to the information gathered and then investigate topic modeling approaches.  ...  Experimental test bed for event mapping is prepared which uses end to end information retrieval system. Lab reports of seizers patients is collected with respective to time and space.  ...  : Continuous Time, infinite Topic This model over comes non-bursty news updates and proposed a hybridization of the infinite topic model and continuous time model which combines Dirichlet process(DP  ... 
doi:10.21275/v5i1.nov152762 fatcat:75zmqmd2jzchpilynld6itvj7a

Bayesian Nonparametric Approaches to Abnormality Detection in Video Surveillance

Vu Nguyen, Dinh Phung, Duc-Son Pham, Svetha Venkatesh
2015 Annals of Data Science  
In particular, we employ the Infinite Hidden Markov Model and Bayesian Nonparametric Factor Analysis for stream data segmentation and pattern discovery.  ...  In data science, anomaly detection is the process of identifying the items, events or observations which do not conform to expected patterns in a dataset.  ...  Fig. 1 1 The infinite Hidden Markov model representation. Left Stochastic process of iHMM.  ... 
doi:10.1007/s40745-015-0030-3 fatcat:56wmpggdgraktipdvg5solnnp4

Engineering Application of Time-changed Lévy Process to Capture Jumps in Stock Market

Xiangqin Zhao, Wang Zhanhaia
2011 Systems Engineering Procedia  
In this paper, under the continuous-time financial framework, we use the time-changed Lévy process with infinite activity and infinite variation to construct the SVNIG model, which can capture small jumps  ...  This model can describe the continuous volatility component and the jump component simultaneously. MCMC approach is then employed to estimate parameters and identify latent variables.  ...  Acknowledgements We are grateful to anonymous referees for their helpful and extensive comments which greatly improved the paper. Responsibility for the paper's content is, however, ours alone.  ... 
doi:10.1016/j.sepro.2011.10.032 fatcat:qkwae6mqvjgylann2kk2d7z3qy

Modelling Placebo Response via Infinite Mixtures

Thaddeus Tarpey, Eva Petkova
2010 JP Journal of Biostatistics  
A flexible infinite mixture model is introduced to model these nonspecific treatment effects.  ...  The infinite mixture model stipulates that the non-specific treatment effects are continuous and this is contrasted with a finite mixture model that is based on the assumption that the non-specific treatment  ...  We thank Erin Tewksbury and Liping Deng for assistance with the data analysis and programming. The authors would like to thank the Eli Lilly Company for providing the data used in this paper.  ... 
pmid:21804745 pmcid:PMC3145361 fatcat:3w62fhlz4fbn7cwzhlqsmrw5du

Unsupervised Event Coreference Resolution

Cosmin Bejan, Sanda Harabagiu
2014 Computational Linguistics  
Furthermore, to overcome some of the limitations of this extension, we devised a new hybrid model, which combines an infinite latent class model with a discrete time series model.  ...  the ability of modeling events described both within the same document and across multiple documents.  ...  Acknowledgments The authors would like to thank the anonymous reviewers, whose insightful comments and suggestions considerably improved the quality of this article.  ... 
doi:10.1162/coli_a_00174 fatcat:ncl4ct5sevgf5cvbp6hw6fv6cu

Tractable nonparametric Bayesian inference in Poisson processes with Gaussian process intensities

Ryan Prescott Adams, Iain Murray, David J. C. MacKay
2009 Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09  
Likelihood-based inference in these models requires an intractable integral over an infinite-dimensional random function.  ...  For nonparametric Bayesian modeling, the Gaussian process is a useful way to place a prior distribution on this intensity.  ...  Acknowledgements The authors wish to thank Maneesh Sahani and Zoubin Ghahramani for valuable comments. Ryan Adams thanks the Gates Cambridge Trust and the Canadian Institute for Advanced Research.  ... 
doi:10.1145/1553374.1553376 dblp:conf/icml/AdamsMM09 fatcat:x3rmmedp7ngufje4454ggan44a

A nested infinite Gaussian mixture model for identifying known and unknown audio events

Yoko Sasaki, Kazuyoshi Yoshii, Satoshi Kagami
2013 2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)  
We propose a nested infinite Gaussian mixture model (iGMM) to represent varied audio events in real environment.  ...  To solve the problem, the proposed method formulates a infinite Gaussian mixture model (iGMM) in which the number of classes are allowed to increase without bound.  ...  The trained model are then used for classifying given audio events into those classes [7] . On the other hand, the proposed method can train an infinite mixture of iGMMs.  ... 
doi:10.1109/wiamis.2013.6616152 dblp:conf/wiamis/SasakiYK13 fatcat:skyu57w2vbatjnvgcw6w5yi3eq

Semiparametric time-to-event modeling in the presence of a latent progression event

John D. Rice, Alex Tsodikov
2016 Biometrics  
Covariates enter the model parametrically as linear combinations that multiply, respectively, the hazard for the latent event and the hazard for the terminal event conditional on the latent one.  ...  To address this problem, we propose a joint model for the unobserved time to the latent and terminal events, with the two events linked by the baseline hazard.  ...  Additional support was provided by "Modeling to Improve Prostate Cancer Outcomes Across Diverse Populations" grant 1U01CA199338 (CISNET).  ... 
doi:10.1111/biom.12580 pmid:27556886 pmcid:PMC5325816 fatcat:ya4mwhxjjrcp3igadnhf73o3bi

Survival Cluster Analysis [article]

Paidamoyo Chapfuwa, Chunyuan Li, Nikhil Mehta, Lawrence Carin, Ricardo Henao
2020 arXiv   pre-print
Experiments on real-world datasets show consistent improvements in predictive performance and interpretability relative to existing state-of-the-art survival analysis models.  ...  In this paper, we propose a Bayesian nonparametrics approach that represents observations (subjects) in a clustered latent space, and encourages accurate time-to-event predictions and clusters (subpopulations  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their insightful comments. This work was supported by NIH/NIBIB R01-EB025020.  ... 
arXiv:2003.00355v1 fatcat:x5m5elmmsrarlja5cszkhgwoly

Online multicamera tracking with a switching state-space model

W. Zajdel, A.T. Cemgil, B.J.A. Krose
2004 Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.  
The model maintains a memory of continuous appearance variables together with discrete latent labels indicating their association.  ...  Our model views every feature vector as a noisy observation from a latent variable that represents underlying object's 'true' appearance.  ...  Y k−1 Y k . as Infinite Gaussian Mixture Model. It allows to introduce new mixture components, when new data arrive.  ... 
doi:10.1109/icpr.2004.1333772 dblp:conf/icpr/ZajdelCK04 fatcat:twyfpl4nljeslpbsqxie3rjr3m

Interactive browsing system for anomaly video surveillance

Tien-Vu Nguyen, Dinh Phung, S. Gupta, S. Venkatesh
2013 2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing  
This paper introduces a novel browsing model to address this issue, allowing users to interactively examine rare events in an intuitive manner.  ...  Rare events correspond to frames that contain the rare factors chosen. We present the user with an interface to inspect events that incorporate these rarest factors in a spatial-temporal manner.  ...  In this nonparametric model, Z is modeled through a draw from beta process which allows infinitely many factors.  ... 
doi:10.1109/issnip.2013.6529821 dblp:conf/issnip/NguyenPGV13 fatcat:a6m6smxoljevdfrag5snjuocoy

Spatiotemporal Clustering with Neyman-Scott Processes via Connections to Bayesian Nonparametric Mixture Models [article]

Yixin Wang, Anthony Degleris, Alex H. Williams, Scott W. Linderman
2022 arXiv   pre-print
This construction is similar to Bayesian nonparametric mixture models like the Dirichlet process mixture model (DPMM) in that the number of latent events (i.e. clusters) is a random variable, but the point  ...  The clustering property is achieved via a doubly stochastic formulation: first, a set of latent events is drawn from a Poisson process; then, each latent event generates a set of observed data points according  ...  This work was funded by grants to SWL from the NIH Brain Initiative (NINDS, U19NS113201 and R01NS113119) and the Simons Collaboration on the Global Brain (SCGB, 697092).  ... 
arXiv:2201.05044v2 fatcat:pbkpzp7urzd6ja2yd7a4f6e6pa
« Previous Showing results 1 — 15 out of 27,659 results