A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Hierarchical Mixtures of Experts and the EM Algorithm
1994
Neural Computation
The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coe cients and the mixture components are generalized linear models (GLIM's). ...
Learning is treated as a maximum likelihood problem in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. ...
Acknowledgements: We w ant to thank Geo rey Hinton, Tony Robinson, Mitsuo Kawato, and Daniel Wolpert for helpful comments on the manuscript. ...
doi:10.1162/neco.1994.6.2.181
fatcat:clexcziqrrdbjae5tezs5mvznm
Hierarchical Mixtures of Experts and the EM Algorithm
[chapter]
1994
ICANN '94
The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coe cients and the mixture components are generalized linear models (GLIM's). ...
Learning is treated as a maximum likelihood problem in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. ...
Acknowledgements: We w ant to thank Geo rey Hinton, Tony Robinson, Mitsuo Kawato, and Daniel Wolpert for helpful comments on the manuscript. ...
doi:10.1007/978-1-4471-2097-1_113
fatcat:fmwk7s7lqbgzda5uq3ewqqnyfy
Hierarchical mixtures of experts and the EM algorithm
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan)
The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coe cients and the mixture components are generalized linear models (GLIM's). ...
Learning is treated as a maximum likelihood problem in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. ...
Acknowledgements: We w ant to thank Geo rey Hinton, Tony Robinson, Mitsuo Kawato, and Daniel Wolpert for helpful comments on the manuscript. ...
doi:10.1109/ijcnn.1993.716791
fatcat:cn6xnhjaqrcc5dvkapc6huyh4a
Normalized Gaussian Network Based on Variational Bayes Inference and Hierarchical Model Selection
変分法的ベイズ推定法に基づく正規化ガウス関数ネットワークと階層的モデル選択法
2003
Transactions of the Society of Instrument and Control Engineers
変分法的ベイズ推定法に基づく正規化ガウス関数ネットワークと階層的モデル選択法
We introduce a hierarchical prior distribution of the model parameters and the NGnet is trained based on the variational Bayes (VB) inference. ...
The performance of our method is evaluated by using function approximation and nonlinear dynamical system identification problems. Our method achieved better performance than existing methods. ...
Thesis, Department of Engineering, University of Cambridge (1997) 18) M.I. Jordan and R.A. Jacobs: Hierarchical mixtures of experts and the EM algorithm, ...
doi:10.9746/sicetr1965.39.503
fatcat:bwsnt6at3vdclij6xktdugvtoy
Page 183 of Neural Computation Vol. 6, Issue 2
[page]
1994
Neural Computation
Mixtures of Experts and EM Algorithm 183
structured approach to estimation that is reminiscent of CART, MARS, and ID3.
The remainder of the paper proceeds as follows. ...
We first introduce the hierarchical mixture-of-experts architecture and present the likelihood function for the architecture. ...
Page 151 of Neural Computation Vol. 8, Issue 1
[page]
1996
Neural Computation
On the convergence properties of the EM algorithm. Ann. Stat. 11, 95-103.
Xu, L., and Jordan, M. I. 1993a. Unsupervised learning by EM algorithm based on finite mixture of Gaussians. Proc. ...
Theoretical and Experimental Studies of the EM Algorithm for Unsupervised Learning Based on Finite Gaussian Mixtures. MIT Computational Cognitive Science, Tech. ...
Non-Normal Mixtures of Experts
[article]
2015
arXiv
pre-print
We develop dedicated expectation-maximization (EM) and expectation conditional maximization (ECM) algorithms to estimate the parameters of the proposed models by monotonically maximizing the observed data ...
Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification and clustering. ...
The EM algorithms are indeed very popular and successful estimation algorithms for mixture models in general and for mixture of experts in particular. ...
arXiv:1506.06707v2
fatcat:5vz7u462wnbrdagdajfsaeqis4
Hierarchical Routing Mixture of Experts
[article]
2019
arXiv
pre-print
Further, we develop a probabilistic framework for the HRME model, and propose a recursive Expectation-Maximization (EM) based algorithm to learn both the tree structure and the expert models. ...
Addressing these problems, we propose a binary tree-structured hierarchical routing mixture of experts (HRME) model that has classifiers as non-leaf node experts and simple regression models as leaf node ...
Hierarchical Routing Mixture of Experts In this section, we present the specifications of the HRME model, formulate the optimization objective, and develop the optimization algorithm. ...
arXiv:1903.07756v1
fatcat:xc32dajwnfahtd55vgf767z4xq
Constructive Algorithms for Hierarchical Mixtures of Experts
1995
Neural Information Processing Systems
We present two additions to the hierarchical mixture of experts (HME) architecture. ...
We demonstrate results for the growing and path pruning algorithms which show significant speed ups and more efficient use of parameters over the standard fixed structure in discriminating between two ...
CLASSIFICATION USING HIERARCHICAL MIXTURES OF EXPERTS The mixture of experts, shown in Figure 1 , consists of a set of "experts" which perform local function approximation . ...
dblp:conf/nips/WaterhouseR95
fatcat:vyxkz4r2wfdofnmeqbewzwooju
A mixture of experts model for rank data with applications in election studies
2008
Annals of Applied Statistics
Model fitting is achieved via a hybrid of the EM and MM algorithms. An example of the methodology is illustrated by examining an Irish presidential election. ...
A mixture of experts model is a mixture model in which the model parameters are functions of covariates. ...
Adrian Raftery, the members of the Center for Statistics and the Social Sciences and the members of the Working Group on Model-based Clustering at the University of Washington for numerous suggestions ...
doi:10.1214/08-aoas178
fatcat:dlvixib4qvg77fasbjk6urihta
Robust mixture of experts modeling using the t distribution
2016
Neural Networks
Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification, and clustering. ...
We develop a dedicated expectation-maximization (EM) algorithm to estimate the parameters of the proposed model by monotonically maximizing the observed data log-likelihood. ...
One interesting future direction is therefore to extend the proposed models to the hierarchical MoE framework (Jordan and Jacobs, 1994) . ...
doi:10.1016/j.neunet.2016.03.002
pmid:27093693
fatcat:x26wnvse5vf7zixakz57goa7w4
A flexible probabilistic framework for large-margin mixture of experts
2019
Machine Learning
Crucially, neither of the two popular gating networks used in MoE, namely the softmax gating network and hierarchical gating network (the latter used in the hierarchical mixture of experts), have efficient ...
Mixture-of-Experts (MoE) enable learning highly nonlinear models by combining simple expert models. ...
The gating networks can learn a flat or a hierarchical partitioning of the input space (the latter being the case with hierarchical mixture of experts Bishop and Svenskn 2002) . ...
doi:10.1007/s10994-019-05811-4
fatcat:lxfqyduzvzh6nc242lm5m3q4ja
A hierarchical mixture model for software reliability prediction
2007
Applied Mathematics and Computation
This is an application of the hierarchical mixtures of experts (HME) architecture. In HMSRM, individual software reliability models are used as experts. ...
During the training of HMSRM, an Expectation-Maximizing (EM) algorithm is employed to estimate the parameters of the model. ...
HMSRM can be considered as an application of the hierarchical mixtures of experts (HME) architecture [9] . ...
doi:10.1016/j.amc.2006.07.028
fatcat:3hpgmigs7rbwnitj7yd4ngo4x4
Hierarchical Methods for Landmine Detection with Wideband Electro-Magnetic Induction and Ground Penetrating Radar Multi-Sensor Systems
2008
IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium
The EM algorithm is used to estimate the parameters of the hierarchical mixture. ...
All four features from WEMI and GPR are used in a Hierarchical Mixture of Experts model to increase the landmine detection rate. ...
HIERARCHICAL MIXTURE OF EXPERTS Hierarchical Mixtures of Experts is a tree structure introduced by Jacobs et al. ...
doi:10.1109/igarss.2008.4778956
dblp:conf/igarss/YukselRGWHH08
fatcat:ygn3ie6sd5gtvcmeaa4uvdwyuu
Learning Ambiguities Using Bayesian Mixture of Experts
2006
Proceedings - International Conference on Tools with Artificial Intelligence, TAI
Mixture of Experts training involve learning a multi-category classifier for the gates distribution and fitting a regressor within each of the clusters. ...
Mixture of Experts(ME) is an ensemble of function ap- proximators that fit the clustered data set locally rather than globally. ...
Bayesian Mixture of Experts Mixture of Experts training involves learning the experts and the gates distribution. ...
doi:10.1109/ictai.2006.73
dblp:conf/ictai/KanaujiaM06
fatcat:vcye635jdfczzbwh475c57cyiq
« Previous
Showing results 1 — 15 out of 5,455 results