G. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents
Tuning the Multivariate Poisson Mixture Model for.. - Brijs, Karlis.. (2002) (Correct)
....user groups will help the retail category manager to optimize his marketing mix towards different customer subgroups. In this context, the use of mixture models (also called model based clustering) has recently gained increased attention as a statistically grounded approach to clustering [16, 18, 20]. More specifically, the multivariate Poisson mixture model will be introduced in this paper and it will be shown that the fullyparameterized model can be greatly simplified by preliminary statistical analysis of the existing purchase interactions in the transactional data, which will enable to ....
....density of the vector y is a mixture density of the form f(Yi) Pf(Yi 10) where 0 p 1, and p = 1 are the mixing proportions. Note that the mixing proportion is the probability that a randomly selected observation belongs to thej th cluster. This is the classical mixture model (see [4, 18]) The purpose of model based clustering is to estimate the parameters (P . Pk ,0 . 0k) Following the maximum likelihood (ML) estimation approach, this involves maximizing the loglikelihood L(y;O,p) ln pjf(y l O j) i=1 j=l which is not easy since there is often not a closed form ....
[Article contains additional citation context not shown here]
McLachlan, G., and Peel, D., Finite mixture models, Wiley series in probability and statistics, 2000.
Generalized Proximal Point Algorithms - Chrétien, III (Correct)
....introduced in [5] a class of methods for statistical estimation which can be recast into the generalized proximal point framework (1. 2) As an important instance, it was shown in [5, 4] that the well known EM algorithm of Dempster et al. 7] extensively used for maximum likelihood estimation [25, 10] is a generalized proximal point procedure of the form (1.2) where (x; y) is a Kullback Leibler divergence between two density functions k(u; x) and k(u; y) parameterized by deterministic vectors x and y respectively, i.e. D k(u; x) log k(u; y) k(u; x) du; 1.4) where D is the complete ....
....by deterministic vectors x and y respectively, i.e. D k(u; x) log k(u; y) k(u; x) du; 1.4) where D is the complete data space in the EM literature . The EM iteration, although non quadratic, enjoys closed form expressions in many important applications, e.g. computerized tomography [37, 25], or mixture densities estimation [25] 3] and More precisely, the quantity is well de ned if the measures k(u; x)du and k(u; y)du are absolutely continuous with respect to each other. In most applications in statistics, this assumption is satis ed. 30] Other extensions of the EM ....
[Article contains additional citation context not shown here]
G.J. McLachlan and T. Krishnan. The EM algorithm and extensions. Wiley Interscience, 1997. Wiley series in probability and statistics.
Outlier Modelling in Image Matching - Hasler, Sbaiz, Süsstrunk, Vetterli (Correct)
....part of this papers shows how to apply the outlier model to a particular case of image matching, namely to camera pose estimation. The outlier model enables to express a pose estimation problem as a mixture of inlier versus outliers, and handle outlier rejection like a standard mixture problem [1, 2]. The performance of the model is demonstrated using two different types of experiments: The first experiment shows two aligned pictures, one of them containing an outlier. The proportion of the image covered by the outlier is varied by framing the images of the pair differently. The goal is to ....
G. McLachlan and D. Peel, Finite Mixture Models. Wiley series in Probability and Statistics, New York: John Wiley and Sons, 2000.
Learning Occupancy Grids With Forward Sensor Models - Thrun (2002) (5 citations) (Correct)
....maximization algorithm (in short: EM) 6] which will be described in turn. As we will see, most terms in this log likelihood function can be ignored in the EM solution to this problem. 3. 4 Finding Maps via EM EM is an iterative algorithm that gradually maximizes the expected log likelihood [13, 18]. Initially, EM generates a random map m. It then iterates two steps, an E step, and an M step, which stand for expectation step and maximization step, respectively. In the E step, the expectations over the correspondences are calculated conditioned on a fixed map. The M step calculates the most ....
....respectively. In the E step, the expectations over the correspondences are calculated conditioned on a fixed map. The M step calculates the most likely map based on these expectations. Iterating both steps leads to a sequence of maps that performs hill climbing in the expected log likelihood space [13, 18]. In detail, we have: 1. Initialization. Maps in EM are discrete: Each grid cell is either occupied or free. There is no notion of uncertainty in the map at this level, since EM finds the most likely map unlike conventional occupancy grid mapping algorithms, which estimates posteriors. In 13 ....
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, New York, 1997.
Using EM to Learn Motion Behaviors of Persons with Mobile.. - Bennewitz, Burgard, Thrun (2002) (7 citations) (Correct)
....method extends this approach as it determines both, the clustering and the corresponding motion behaviors. In this paper we present an approach that allows a mobile robot to learn motion patterns of persons, while they are carrying out their every day activities. We use the popular EM algorithm [11] to simultaneously cluster trajectories belonging to one motion behavior and to learn the characteristic motions of this behavior. We apply our technique to data recorded by mobile robots equipped with laser range finders and demonstrate how the learned models can be used to predict the trajectory ....
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Mixture Models and Frequent Sets: Combining Global and.. - Hollmén, Seppänen.. (2003) Self-citation (Models) (Correct)
No context found.
G. McLachlan and D. Peel, Finite Mixture Models, Wiley Series in Probability and Statistics, John Wiley & Sons, 2000.
Computer Vision for Music Identification - Yan Ke Derek (2005) (Correct)
No context found.
G. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Sparse Audio Representations Using the MCLT - Davies, Daudet (2005) (Correct)
No context found.
G.J. McLachlin and T. Krishnan, The EM Algorithm and Extensions, Wiley Series in Probability and Statistics, 1997.
Fast Sparse Subband Decomposition Using FIRSP - Davies, Daudet (2004) (Correct)
No context found.
G.J. McLachlin and T. Krishnan, The EM Algorithm and Extensions, Wiley Series in Probability and Statistics, 1997.
Automatic Derivation of Statistical Data Analysis.. - Fischer, Hajian.. (2003) (Correct)
No context found.
McLachlan, G., and Krishnan, T., The EM Algorithm and Extensions, Wiley Series in Probability and Statistics, John Wiley & Sons, 1997.
Computer Vision for Music Identification - Yan Ke Derek (2005) (Correct)
No context found.
G. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Utilizing Learned Motion Patterns to Robustly Track Persons - Bennewitz, Burgard, Cielniak (2003) (1 citation) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Where is . . . ? Learning and Utilizing Motion.. - Cielniak, Bennewitz.. (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Is Robotics Going Statistics? - The Field Of (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, New York, 1997.
Integrating Inconsistent Data in a Probabilistic Model - Vomlel (2003) (Correct)
No context found.
G. J. McLachlan and T. Krishnan. The EM algorithm and extensions. Wiley series in probability and statistics. John Wiley & Sons, Inc., 1997.
Utilizing Learned Motion Patterns to Robustly Track Persons - Bennewitz, Burgard, Cielniak (2003) (1 citation) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Where is . . . ? Learning and Utilizing Motion.. - Cielniak, Bennewitz.. (2003) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, 1997.
Robust Tracking of Athletes - Using Multiple Features (2004) (Correct)
No context found.
McLachlan, G.J., Krishnan, T. The EM algorithm and extensions. Wiley Series in Probability and Statistics, John Wiley & Sons, Inc., 1997.
Atlanta World: An Expectation Maximization Framework for.. - Schindler, Dellaert (2004) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM algorithm and extensions. Wiley series in probability and statistics. John Wiley & Sons, 1997.
Retrofitting the Retrofitting the AutoBayes Program Synthesis .. - Fischer, Visser (2004) (Correct)
No context found.
G. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics. John Wiley & Sons, New York, 1997.
Noisy-Or Classifier - Jir Vomlel Laboratory (2003) (Correct)
No context found.
G. J. McLachlan and T. Krishnan. The EM algorithm and extensions. Wiley series in probability and statistics. John Wiley & Sons, Inc., 1997.
Atlanta World: An Expectation Maximization Framework for.. - Schindler, Dellaert (2004) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM algorithm and extensions. Wiley series in probability and statistics. John Wiley & Sons, 1997.
An Adaptive Bayesian Wavelet Thresholding Approach To.. - Abd-Krim Seghouane.. (2004) (Correct)
No context found.
G. J. McLachlan, T. Krishnan, The EM Algorithm and Extensions, Wiley series in probability and statistics, 1997. 271
Robotic Mapping: A Survey - Thrun (2002) (31 citations) (Correct)
No context found.
G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Wiley Series in Probability and Statistics, New York, 1997.
From Low Level Features To High Level - Zhang (Correct)
No context found.
G. McLachlan, and T. Krishnan, The EM algorithm and Extensions. Wiley series in probability and statistics. John Wiley & Sons. (1997).
First 50 documents
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC