The expectation-maximization algorithm

Moon, Todd K.

doi:10.1109/79.543975

Cited by 2,517 publications

(1,181 citation statements)

References 36 publications

Supporting

Mentioning

1,120

Contrasting

Unclassified

Order By: Relevance

“…Expectation-maximization (EM) algorithm [6], which is an iterative procedure that maximizes the likelihood of Gaussian mixtures models (GMM), is well known as easy and convenient means to approximate GMM to the non Gaussian distributions. However, all GMMs given by this fitting algorithm tend to concentrate in the non-tail region in which the sensitivity to increase the likelihood is much larger than that for the tail region, as shown in Fig.…”

Section: Discussion On the Conventional Modelsmentioning

confidence: 99%

Adaptive Segmentation Gaussian Mixtures Models for Approximating to Drastically Scaled-Various Sloped Long-Tail RTN Distributions

Somha¹,

Yamauchi²

2013

IJFCC

View full text Add to dashboard Cite

Abstract-This paper proposes a fitting method to approximate the mixtures of various sloped-tail Gamma distribution characterizing the random telegraph noises (RTN) by an adaptive segmentation Gaussian mixtures model (GMM). The concepts central to the proposed method are 1) adaptive segmentation of the long-heavy tailed distributions such that the log-likelihood of GMM in each partition is maximized and 2) copy and paste with an adequate weight into each partition. This allows the fitting model to apply various bounded tail distribution even with multiple convex and concave folding curves. It is verified that the proposed method can reduce the error of the fail-bit predictions by 2-orders of magnitude while reducing the iterations for EM step convergence to 1/16 at the interest point of the fail probability of 10 -12 which corresponds to the design point to realize a 99.9% yield of 1Gbit chips.Index Terms-Mixtures of Gaussian, random telegraph noise, em algorithm, heavy-tail distribution, long-tail distribution, fail-bit analysis, static random access memory, guard band design.

show abstract

Section: Discussion On the Conventional Modelsmentioning

confidence: 99%

Adaptive Segmentation Gaussian Mixtures Models for Approximating to Drastically Scaled-Various Sloped Long-Tail RTN Distributions

Somha¹,

Yamauchi²

2013

IJFCC

View full text Add to dashboard Cite

show abstract

“…Basis learning methods are mostly based on the expectationmaximization (EM) algorithm [41]. They alternate between an expectation step that estimates the coefficients, and a maximization step that optimizes the vectors.…”

Section: Basis Learningmentioning

confidence: 99%

Decomposition and dictionary learning for 3D trajectories

2014

View full text Add to dashboard Cite

A new model for describing a three-dimensional (3D) trajectory is proposed in this article. The studied trajectory is viewed as a linear combination of rotatable 3D patterns. The resulting model is thus 3D rotation invariant (3DRI). Moreover, the temporal patterns are considered as shift-invariant. This article is divided into two parts based on this model. On the one hand, the 3DRI decomposition estimates the active patterns, their coefficients, their rotations and their shift parameters. Based on sparse approximation, this is carried out by two non-convex optimizations: 3DRI matching pursuit (3DRI-MP) and 3DRI orthogonal matching pursuit (3DRI-OMP). On the other hand, a 3DRI learning method learns the characteristic patterns of a database through a 3DRI dictionary learning algorithm (3DRI-DLA). The proposed algorithms are first applied to simulation data to evaluate their performances and to compare them to other algorithms. Then, they are applied to real motion data of cued speech, to learn the 3D trajectory patterns characteristic of this gestural language.

show abstract

“…It partitions the data into k clusters, starting from centroids, and computing the fitness with the help of the Euclidian distance. The second algorithm employed is the Expectation Maximization (EM) [8], another well known method. It functions by maximizing the log likelihood of a function by multiple iterations.…”

Section: Data Mining Phasementioning

confidence: 99%

“…Clustering methods are used in the financial area, as collected data volumes and the need to obtain accurate analysis on the natural structure of it are increasing. Classic clustering methods such as kmeans [7], Expectation Maximization [8], but also density based methods like DBSCAN [9] and OPTICS [10] are nowadays used in practice. Also, methods for data stream clustering are used, especially created for rapidly changing environments (e.g.…”

Section: Related Workmentioning

confidence: 99%