Search For:

Displaying 1-35 out of 35 total
Semisupervised Multitask Learning
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Qiuhua Liu, Xuejun Liao, Hui Li Carin, Jason R. Stack, Lawrence Carin
Issue Date:June 2009
pp. 1074-1086
Context plays an important role when performing classification, and in this paper we examine context from two perspectives. First, the classification of items within a single task is placed within the context of distinct concurrent or previous classificati...
 
Sparse Multinomial Logistic Regression: Fast Algorithms and Generalization Bounds
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Balaji Krishnapuram, Lawrence Carin, Mário A.T. Figueiredo, Alexander J. Hartemink
Issue Date:June 2005
pp. 957-968
Recently developed methods for learning sparse classifiers are among the state-of-the-art in supervised learning. These methods learn classifiers that incorporate weighted sums of basis functions with sparsity-promoting priors encouraging the weight estima...
 
Deep Learning with Hierarchical Convolutional Factor Analysis
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bo Chen,Gungor Polatkan,Guillermo Sapiro,David Blei,David Dunson,Lawrence Carin
Issue Date:August 2013
pp. 1887-1901
Unsupervised multilayered (“deep”) models are considered for imagery. The model is represented using a hierarchical convolutional factor-analysis construction, with sparse factor loadings and scores. The computation of layer-dependent...
 
Hierarchical factor modeling of proteomics data
Found in: Computational Advances in Bio and Medical Sciences, IEEE International Conference on
By Ricardo Henao,J. Will Thompson,M. Arthur Moseley,Geoffrey S. Ginsburg,Lawrence Carin,Joseph E. Lucas
Issue Date:February 2012
pp. 1-6
This paper presents a hierarchical bayesian factor model specifically designed to model the known correlation structure of both peptides and proteins in unbiased, label free proteomics. The model utilizes partial identification information from peptide seq...
 
Hierarchical Bayesian Modeling of Topics in Time-Stamped Documents
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Iulian Pruteanu-Malinici, Lu Ren, John Paisley, Eric Wang, Lawrence Carin
Issue Date:June 2010
pp. 996-1011
We consider the problem of inferring and modeling topics in a sequence of documents with known publication dates. The documents at a given time are each characterized by a topic and the topics are drawn from a mixture model. The proposed model infers the c...
 
Active learning for semi-supervised multi-task learning
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Hui Li, Xuejun Liao, Lawrence Carin
Issue Date:April 2009
pp. 1637-1640
We present an algorithm for active learning (adaptive selection of training data) within the context of semi-supervised multi-task classifier design. The semi-supervised multi-task classifier exploits manifold information provided by the unlabeled data, wh...
 
Dirichlet process mixture models with multiple modalities
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By John Paisley, Lawrence Carin
Issue Date:April 2009
pp. 1613-1616
The Dirichlet process can be used as a nonparametric prior for an infinite-dimensional probability mass function on the parameter space of a mixture model. The set of parameters over which it is defined is generally used for a single, parametric distributi...
 
Music analysis with a Bayesian dynamic model
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Lu Ren, David B. Dunson, Scott Lindroth, Lawrence Carin
Issue Date:April 2009
pp. 1681-1684
A Bayesian dynamic model is developed to model complex sequential data, with a focus on audio signals from music. The music is represented in terms of a sequence of discrete observations, and the sequence is modeled using a hidden Markov model (HMM) with t...
 
Cybersecurity Strategies: The QuERIES Methodology
Found in: Computer
By Lawrence Carin, George Cybenko, Jeff Hughes
Issue Date:August 2008
pp. 20-26
QuERIES offers a novel multidisciplinary approach to quantifying risk associated with security technologies resulting in investment-efficient cybersecurity strategies.
 
Semisupervised Learning of Hidden Markov Models via a Homotopy Method
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shihao Ji, Layne T. Watson, Lawrence Carin
Issue Date:February 2009
pp. 275-287
Hidden Markov model (HMM) classifier design is considered for the analysis of sequential data, incorporating both labeled and unlabeled data for training; the balance between the use of labeled and unlabeled data is controlled by an allocation parameter \l...
 
In Situ Compressive Sensing
Found in: Statistical Signal Processing, IEEE/SP Workshop on
By Lawrence Carin, Dehong Liu, Ya Xue
Issue Date:August 2007
pp. 322-325
Compressive sensing (CS) is a framework that exploits the compressible character of most natural signals, allowing the accurate measurement of an m-dimensional real signal u in terms of n
 
On Classification with Incomplete Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David Williams, Xuejun Liao, Ya Xue, Lawrence Carin, Balaji Krishnapuram
Issue Date:March 2007
pp. 427-436
We address the incomplete-data problem in which feature vectors to be classified are missing data (features). A (supervised) logistic regression algorithm for the classification of incomplete data is developed. Single or multiple imputation for the missing...
 
Variational Bayes for Continuous Hidden Markov Models and Its Application to Active Learning
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shihao Ji, Balaji Krishnapuram, Lawrence Carin
Issue Date:April 2006
pp. 522-532
In this paper, we present a varitional Bayes (VB) framework for learning continuous hidden Markov models (CHMMs), and we examine the VB framework within active learning. Unlike a maximum likelihood or maximum a posteriori training procedure, which yield a ...
 
A Bayesian Approach to Unsupervised Feature Selection and Density Estimation Using Expectation Propagation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shaorong Chang, Nilanjan Dasgupta, Lawrence Carin
Issue Date:June 2005
pp. 1043-1050
We propose an approximate Bayesian approach for unsupervised feature selection and density estimation, where the importance of the features for clustering is used as the measure for feature selection. Traditional maximum-likelihood (ML) model-parameter opt...
 
A Bayesian Approach to Joint Feature Selection and Classifier Design
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Balaji Krishnapuram, Alexander J. Hartemink, Lawrence Carin, Mário A.T. Figueiredo
Issue Date:September 2004
pp. 1105-1111
This paper adopts a Bayesian approach to simultaneously learn both an optimal nonlinear classifier and a subset of predictor variables (or features) that are most relevant to the classification task. The approach uses heavy-tailed priors to promote sparsit...
 
Application of the Theory of Optimal Experiments to Adaptive Electromagnetic-Induction Sensing of Buried Targets
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xuejun Liao, Lawrence Carin
Issue Date:August 2004
pp. 961-972
<p><b>Abstract</b>—A mobile electromagnetic-induction (EMI) sensor is considered for detection and characterization of buried conducting and/or ferrous targets. The sensor may be placed on a robot and, here, we consider design of an optim...
 
Rate-Distortion Analysis of Discrete-HMM Pose Estimation via Multiaspect Scattering Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yanting Dong, Lawrence Carin
Issue Date:July 2003
pp. 872-883
<p><b>Abstract</b>—We consider the problem of estimating the pose of a target based on a sequence of scattered waveforms measured at multiple target-sensor orientations. Using a hidden Markov model (HMM) representation of the scattered-wa...
 
Rate-Distortion Bound for Joint Compression and Classification
Found in: Data Compression Conference
By Yanting Dong, Lawrence Carin
Issue Date:March 2003
pp. 423
No summary available.
   
Infrared-Image Classification Using Hidden Markov Trees
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Priya Bharadwaj, Lawrence Carin
Issue Date:October 2002
pp. 1394-1398
<p><b>Abstract</b>—An image of a three-dimensional target is generally characterized by the visible target subcomponents, with these dictated by the target-sensor orientation (target pose). An image often changes quickly with variable pos...
 
Genetic Algorithm Wavelet Design for Signal Classification
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Eric Jones, Paul Runkle, Nilanjan Dasgupta, Luise Couchman, Lawrence Carin
Issue Date:August 2001
pp. 890-895
<p><b>Abstract</b>—Biorthogonal wavelets are applied to parse multiaspect transient scattering data in the context of signal classification. A language-based genetic algorithm is used to design wavelet filters that enhance classification ...
 
Multiaspect Target Identification with Wave-Based Matched Pursuits and Continuous Hidden Markov Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Paul Runkle, Lawrence Carin, Luise Couchman, Timothy J. Yoder, Joseph A. Bucaro
Issue Date:December 1999
pp. 1371-1378
<p><b>Abstract</b>—Multiaspect target identification is effected by fusing the features extracted from multiple scattered waveforms; these waveforms are characteristic of viewing the target from a <it>sequence</it> of distinct...
 
A Bayesian Nonparametric Approach to Image Super-resolution
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gungor Polatkan,David Blei,Ingrid Daubechies,Lawrence Carin,Mingyuan Zhou
Issue Date:May 2014
pp. 1
Super-resolution methods form high-resolution images from low-resolution images. In this paper, we develop a new Bayesian nonparametric model for super-resolution. Our method uses a beta-Bernoulli process to learn a set of recurring visual patterns, called...
 
Negative Binomial Process Count and Mixture Modeling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Mingyuan Zhou,Lawrence Carin
Issue Date:November 2013
pp. 1
The seemingly disjoint problems of count and mixture modeling are united under the negative binomial (NB) process. A gamma process is employed to model the rate measure of a Poisson process, whose normalization provides a random probability measure for mix...
 
Negative Binomial Process Count and Mixture Modeling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Mingyuan Zhou,Lawrence Carin
Issue Date:October 2013
pp. 1
The seemingly disjoint problems of count and mixture modeling are united under the negative binomial (NB) process. A gamma process is employed to model the rate measure of a Poisson process, whose normalization provides a random probability measure for mix...
 
Multi-task classification with infinite local experts
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Chunping Wang, Qi An, Lawrence Carin, David B. Dunson
Issue Date:April 2009
pp. 1569-1572
We propose a multi-task learning (MTL) framework for non-linear classification, based on an infinite set of local experts in feature space. The usage of local experts enables sharing at the expert-level, encouraging the borrowing of information even if tas...
 
Active learning for online bayesian matrix factorization
Found in: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '12)
By Jorge Silva, Lawrence Carin
Issue Date:August 2012
pp. 325-333
The problem of large-scale online matrix completion is addressed via a Bayesian approach. The proposed method learns a factor analysis (FA) model for large matrices, based on a small number of observed matrix elements, and leverages the statistical model t...
     
The contextual focused topic model
Found in: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '12)
By Lawrence Carin, Mingyuan Zhou, Xu Chen
Issue Date:August 2012
pp. 96-104
A nonparametric Bayesian contextual focused topic model (cFTM) is proposed. The cFTM infers a sparse ("focused") set of topics for each document, while also leveraging contextual information about the author(s) and document venue. The hierarchical beta pro...
     
Nonparametric factor analysis with beta process priors
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By John Paisley, Lawrence Carin
Issue Date:June 2009
pp. 1-8
We propose a nonparametric extension to the factor analysis problem using a beta process prior. This beta process factor analysis (BP-FA) model allows for a dataset to be decomposed into a linear combination of a sparse set of factors, providing informatio...
     
The dynamic hierarchical Dirichlet process
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By David B. Dunson, Lawrence Carin, Lu Ren
Issue Date:July 2008
pp. 824-831
The dynamic hierarchical Dirichlet process (dHDP) is developed to model the time-evolving statistical properties of sequential data sets. The data collected at any time point are represented via a mixture associated with an appropriate underlying model, in...
     
Multi-task compressive sensing with Dirichlet process priors
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By David Dunson, Dehong Liu, Lawrence Carin, Yuting Qi
Issue Date:July 2008
pp. 768-775
Compressive sensing (CS) is an emerging £eld that, under appropriate conditions, can signi£cantly reduce the number of measurements required for a given signal. In many applications, one is interested in multiple signals that may be measured in...
     
Hierarchical kernel stick-breaking process for multi-task image analysis
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By Chunping Wang, David B. Dunson, Eric Wang, Ivo Shterev, Lawrence Carin, Qi An
Issue Date:July 2008
pp. 17-24
The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the condition that patches (small blocks of pixels) that are spatially proximate are more likely to be associated with the same cluster (segment). The number of clust...
     
Region-based value iteration for partially observable Markov decision processes
Found in: Proceedings of the 23rd international conference on Machine learning (ICML '06)
By Hui Li, Lawrence Carin, Xuejun Liao
Issue Date:June 2006
pp. 561-568
An approximate region-based value iteration (RBVI) algorithm is proposed to find the optimal policy for a partially observable Markov decision process (POMDP). The proposed RBVI approximates the true polyhedral partition of the belief simplex with an ellip...
     
Incomplete-data classification using logistic regression
Found in: Proceedings of the 22nd international conference on Machine learning (ICML '05)
By David Williams, Lawrence Carin, Xuejun Liao, Ya Xue
Issue Date:August 2005
pp. 972-979
A logistic regression classification algorithm is developed for problems in which the feature vectors may be missing data (features). Single or multiple imputation for the missing data is avoided by performing analytic integration with an estimated conditi...
     
Logistic regression with an auxiliary data source
Found in: Proceedings of the 22nd international conference on Machine learning (ICML '05)
By Lawrence Carin, Xuejun Liao, Ya Xue
Issue Date:August 2005
pp. 505-512
To achieve good generalization in supervised learning, the training and testing examples are usually required to be drawn from the same source distribution. In this paper we propose a method to relax this requirement in the context of logistic regression. ...
     
Joint classifier and feature optimization for cancer diagnosis using gene expression data
Found in: Proceedings of the seventh annual international conference on Computational molecular biology (RECOMB '03)
By Alexander J. Hartemink, Balaji Krishnapuram, Lawrence Carin
Issue Date:April 2003
pp. 167-175
Recent research has demonstrated quite convincingly that accurate cancer diagnosis can be achieved by constructing classifiers that are designed to compare the gene expression profile of a tissue of unknown cancer status to a database of stored expression ...
     
 1