论文信息 - Products of Gaussians

Products of Gaussians

Recently Hinton (1999) has introduced the Products of Experts (PoE) model in which several individual probabilistic models for data are combined to provide an overall model of the data. Below we consider PoE models in which each expert is a Gaussian. Although the product of Gaussians is also a Gaussian, if each Gaussian has a simple structure the product can have a richer structure. We examine (1) Products of Gaussian pancakes which give rise to probabilistic Minor Components Analysis, (2) products of 1-factor PPCA models and (3) a products of experts construction for an AR(1) process.

Christopher K. I. Williams | Felix V. Agakov | Stephen N. Felderhof | F. Agakov

[1] Erkki Oja,et al. Principal components, minor components, and linear neural networks , 1992, Neural Networks.

[2] W. Clem Karl,et al. Multiscale representations of Markov random fields , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3] John G. Proakis,et al. Digital signal processing (2nd ed.): principles, algorithms, and applications , 1992 .

[4] Michael E. Tipping,et al. Probabilistic Principal Component Analysis , 1999 .

[5] Erkki Oja,et al. Neural Nets for Dual Subspace Pattern Recognition Method , 1991, Int. J. Neural Syst..

[6] Javier R. Movellan,et al. Diffusion Networks, Products of Experts, and Factor Analysis , 2001 .

[7] Christopher K. I. Williams,et al. Products of Gaussians and Probabilistic Minor Component Analysis , 2002, Neural Computation.

[8] William H. Press,et al. Numerical recipes in C , 2002 .

[9] Geoffrey E. Hinton. Products of experts , 1999 .

[10] John G. Proakis,et al. Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .