The BYY annealing learning algorithm for Gaussian mixture with automated model selection

Authors:
Jinwen Ma;Jianfeng Liu
Affiliations:
Department of Information Science, School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China;Department of Information Science, School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China
Venue:
Pattern Recognition
Year:
2007

Citing 7
Cited 12

Bayesian Ying-Yang machine, clustering and number of clusters

Pattern Recognition Letters - special issue on pattern recognition in practice V
Deterministic annealing EM algorithm

Neural Networks
Pairwise Data Clustering by Deterministic Annealing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian model search for mixture models based on optimizing variational bounds

Neural Networks
BYY harmony learning, structural RPCL, and topological self-organizing on mixture models

Neural Networks - New developments in self-organizing maps
BYY Harmony Learning on Finite Mixture: Adaptive Gradient Implementation and A Floating RPCL Mechanism

Neural Processing Letters
Rival penalized competitive learning for clustering analysis, RBF net, and curve detection

IEEE Transactions on Neural Networks

A fast fixed-point BYY harmony learning algorithm on Gaussian mixture with automated model selection

Pattern Recognition Letters
The Competitive EM Algorithm for Gaussian Mixtures with BYY Harmony Criterion

ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Automatic Straight Line Detection through Fixed-Point BYY Harmony Learning

ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
BYY Harmony Learning on Weibull Mixture with Automated Model Selection

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
A BYY Split-and-Merge EM Algorithm for Gaussian Mixture Learning

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
A Gradient BYY Harmony Learning Algorithm for Straight Line Detection

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Parameter estimation of Poisson mixture with automated model selection through BYY harmony learning

Pattern Recognition
An adaptive gradient BYY learning rule for poisson mixture with automated model selection

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
Simultaneous model selection and feature selection via BYY harmony learning

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
A fixed-point EM algorithm for straight line detection

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
k'-Means algorithms for clustering analysis with frequency sensitive discrepancy metrics

Pattern Recognition Letters
Kernel k'-means algorithm for clustering analysis

ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories and Technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

Bayesian Ying-Yang (BYY) learning has provided a new mechanism that makes parameter learning with automated model selection via maximizing a harmony function on a backward architecture of the BYY system for the Gaussian mixture. However, since there are a large number of local maxima for the harmony function, any local searching algorithm, such as the hard-cut EM algorithm, does not work well. In order to overcome this difficulty, we propose a simulated annealing learning algorithm to search the global maximum of the harmony function, being expressed as a kind of deterministic annealing EM procedure. It is demonstrated by the simulation experiments that this BYY annealing learning algorithm can efficiently and automatically determine the number of clusters or Gaussians during the learning process. Moreover, the BYY annealing learning algorithm is successfully applied to two real-life data sets, including Iris data classification and unsupervised color image segmentation.