Adaptive mixture density estimation
Pattern RecognitionPublished 1 May 1993
Carey E. Priebe, David J. Marchette
Citations61
SJR quartileQ1
SJR score2.06
SNIP2.67
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The asymptotic performance of the recursive, nonparametric method, dubbed “adaptive mixtures” for its data-driven development of a mixture model approximation to the true density, is investigated using the method of sieves.
Abstract
A recursive, nonparametric method is developed for performing density estimation derived from mixture models, kernel estimation and stochastic approximation. The asymptotic performance of the method, dubbed "adaptive mixtures" (Priebe and Marchette, Pattern Recognition24, 1197–1209 (1991)) for its data-driven development of a mixture model approximation to the true density, is investigated using the method of sieves. Simulations are included indicating convergence properties for some simple examples.
Keywords
Computer Science
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
49,657 Citations1977A. P. Dempster, N. M. Laird +1 more
Density Estimation for Statistics and Data Analysis
15,768 Citations2018B.W. Silverman
The Annals of Mathematical StatisticsOn Estimation of a Probability Density Function and Mode
10,504 Citations1962Emanuel Parzen
The Economic JournalMathematical Methods of Statistics.
6,007 Citations1947R. C. Geary, H. Leslie Cramer
Digital Access to Scholarship at Harvard (DASH) (Harvard University)Maximum Likelihood from Incomplete Data via the EM Algorithm
4,523 Citations1977Dempster, Arthur P., Laird, Nan M. +1 more
Neural NetworksProbabilistic neural networks
3,738 Citations1990Donald F. Specht
A probabilistic neural network that can compute nonlinear decision boundaries which approach the Bayes optimal is formed, and a fourlayer neural network of the type proposed can map any input pattern to any number of classifications.
Journal of the American Statistical AssociationStatistical Analysis of Finite Mixture Distributions.
2,940 Citations1987Bruce G. Lindsay, D. M. Titterington +2 more
SIAM ReviewMixture Densities, Maximum Likelihood and the EM Algorithm
2,686 Citations1984Richard A. Redner, Homer F. Walker
This work discusses the formulation and theoretical and practical properties of the EM algorithm, a specialization to the mixture density context of a general algorithm used to approximate maximum-likelihood estimates for incomplete data problems.
Encyclopedia of Statistics in Behavioral ScienceFinite Mixture Distributions
1,287 Citations2005Barry J. Everitt
Journal of the American Statistical AssociationNonparametric Density Estimation: The L 1 View.
802 Citations1987James R. Thompson, Luc Devroye +1 more
The Annals of StatisticsOptimal Rates of Convergence for Nonparametric Estimators
790 Citations1980Charles J. Stone
Nature Physical ScienceNon-parametric Roughness Penalty for Probability Densities
413 Citations1971I. J. Good
A method is presented here that should help to overcome the difficulty of deciding whether “bumps” are genuinely in the population.
The Annals of StatisticsNonparametric Maximum Likelihood Estimation by the Method of Sieves
362 Citations1982Stuart Geman, Chii-Ruey Hwang
Journal of the Royal Statistical Society Series B (Statistical Methodology)Recursive Parameter Estimation Using Incomplete Data
323 Citations1984D. M. Titterington
Journal of the American Statistical AssociationTransformations in Density Estimation
284 Citations1991M. P. Wand, J. S. Marron +1 more
This article proposes to transform the data with the intention that a global window width is more appropriate for the density of the transformed data, and explores choosing the transformation from suitable parametric families.
IEEE Transactions on Information TheoryAsymptotically optimal discriminant functions for pattern classification
175 Citations1969C. Wolverton, T. Wagner
It is shown that as the number of labeled samples used to construct the approximations increases, the resulting sequence of discriminant functions is asymptotically optimal in the sense that the probability of misclassification when using the approxIMations in the decision procedure converges in probability or with probability 1, depending on the assumptions made.
Neural NetworksMaximum likelihood neural networks for sensor fusion and adaptive classification
164 Citations1991Leonid Perlovsky, Margaret M. McManus
This paper describes the maximum likelihood artificial neural system (MLANS) and presents examples of its performances in unsupervised, partially supervised, and environment-interrogation modes, and the Cramer-Rao theory as it relates to neural networks.
Bulletin of Mathematical StatisticsSEQUENTIAL ESTIMATION OF A CONTINUOUS PROBABILITY DENSITY FUNCTION AND MODE
109 Citations1971Hajime Yamato
The Annals of Mathematical StatisticsOn Strong Consistency of Density Estimates
109 Citations1969John Van Ryzin
The Annals of StatisticsData-Based Optimal Smoothing of Orthogonal Series Density Estimates
101 Citations1981Grace Wahba
The Annals of StatisticsRemarks on Some Recursive Estimators of a Probability Density
99 Citations1979Edward J. Wegman, H. I. Davies
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe reduced Parzen classifier
92 Citations1989Keinosuke Fukunaga, R.R. Hayes
An algorithm is developed to select a given number of representative samples whose Parzen density estimate closely matches that of the entire sample set, and a piecewise quadratic classifier which provides nearly optimal performance.
Journal of the American Statistical AssociationTransformations in Density Estimation
82 Citations1991M. P. Wand, J. S. Marron +1 more
IEEE Transactions on Information TheoryStochastic estimation of a mixture of normal density functions using an information criterion
56 Citations1970Tzay Y. Young, Giorgio Coraluppi
A stochastic approximation algorithm is developed for estimating a mixture of normal density functions with unknown means and unknown variances that minimizes an information criterion that has interesting properties for density approximations.
IEEE Transactions on Information TheoryUnsupervised learning and the identification of finite mixtures
55 Citations1970S. Yakowitz
It is demonstrated that identification theory implies unsupervised learning is possible in many important cases, and a general method is presented as inclusive as the one revealed here, which is effective for all the many cases wherein unsuper supervised learning is known to be possible.
The Annals of Mathematical StatisticsA Consistent Estimator for the Identification of Finite Mixtures
38 Citations1969S. Yakowitz
Pattern RecognitionAdaptive mixtures: Recursive nonparametric pattern recognition
31 Citations1991Carey E. Priebe, David J. Marchette
A method of performing pattern recognition (discrimination and classification) using a recursive technique derived from mixture models, kernel estimation and stochastic approximation is developed.
Sieves for Nonparametric Estimation of Densities and Regressions.
14 Citations1981Stuart Geman
SIMULATIONAn initial assessment of discriminant surface complexity for power law features
12 Citations1992Jeffrey L. Solka, Carey E. Priebe +1 more
The presence of man-made objects in gray-scale images has been successfully detected using a new class of density estimation neural networks to analyze power law signatures.
Mathematical and Computer ModellingThe Adaptive Kernel Neural Network
8 Citations1990David J. Marchette, Carey E. Priebe
The Adaptive Kernel Neural Network (AKNN) is a density estimation technique closely related to kernel estimation that retains the inherent parallelism that is common in neural network models.