The expectation-maximization algorithm

By Todd K. Moon. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Simultaneous Estimation of Noise and Signal in Cosmic Microwave Background Experiments (1999, methodology): “We note that this algorithm is similar to “Expectation-Maximization” (EM) algorithms (Moon 1996) which alternate between filling in unknown data (as in our mapmaking step) and calculating a maximum-likelihood estimation of some quantity (the power-spectrum estimation step).”
Deep learning for deepfakes creation and detection: A survey (2019, methodology): “Using convolutional traces on GAN-based images [162] KNN, SVM, and LDA Training the expectation-maximization algorithm [163] to detect and extract discriminative features via a fingerprint that represents the convolutional traces left by GANs during image generation.”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, methodology): “Features were extracted using the Expectation Maximization algorithm [67].”
Rare event estimation with sequential directional importance sampling (2022, methodology): “The parameters of the Gaussian mixture model can be estimated with the so-called expectation-maximization (EM) algorithm [41] using the samples obtained after the resampling step.”
On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice (2020, methodology): “The expectation-maximization (EM) algorithm [71] is an iterative algorithm used to detect the maximum likelihood estimation of parameters.”
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning (2022, methodology): “Since the prototype is latent, we further propose to use an expectation-maximization (EM) algorithm [19] to infer the prototypes.”
An empirical comparison of botnet detection methods (2014, methodology): “The technique used for this task is WEKA ' s implementation of the Expectation - Maximization ( EM ) algorithm ( Moon , 1996 ) .”
Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning (2016, methodology): “Given the training set, Expectation maximization (EM) [18] algorithm is used to estimate the parameters of GMM, and k-means [19] is applied to initialize the EM algorithm.”
The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data (2011, background): “A solution to this chicken-and-egg problem is the expectation–maximization (EM) algorithm [27].”
A Novel Framework for the Design of Change-Detection Systems for Very-High-Resolution Remote Sensing Images (2013, methodology): “Statistical class parameters have been estimated with the unsupervised method presented in [31] based on the Expectation-Maximization algorithm [31], [69] [91], [92], [93].”