Probabilistic PCA self-organizing maps

Neural networks
Principal component analysis
Authors

Ezequiel López-Rubio

Juan Miguel Ortiz-de-Lazcano-Lobato

Domingo López-Rodríguez

Published

19 August 2009

Publication details

IEEE Transactions on Neural Networks vol 20 (9), 1474-1489

Links

DOI

 

Abstract

In this paper, we present a probabilistic neural model, which extends Kohonen’s self-organizing map (SOM) by performing a probabilistic principal component analysis (PPCA) at each neuron. Several SOMs have been proposed in the literature to capture the local principal subspaces, but our approach offers a probabilistic model while it has a low complexity on the dimensionality of the input space. This allows to process very high-dimensional data to obtain reliable estimations of the probability densities which are based on the PPCA framework. Experimental results are presented, which show the map formation capabilities of the proposal with high-dimensional data, and its potential in image and video compression applications.

Cites

The following graph plots the number of cites received by this work from its publication, on a yearly basis.

Citation

Please, cite this work as:

[LOL09] E. López-Rubio, J. M. Ortiz-de-Lazcano-Lobato, and D. López-Rodríguez. “Probabilistic PCA Self-Organizing Maps”. In: IEEE Trans. Neural Networks 20.9 (2009), pp. 1474-1489. DOI: 10.1109/TNN.2009.2025888. URL: https://doi.org/10.1109/TNN.2009.2025888.

@article{Lopez-RubioOL09,
     author = {Ezequiel López{-}Rubio and
     Juan Miguel Ortiz{-}de{-}Lazcano{-}Lobato and
     Domingo López{-}Rodríguez},
     title = {Probabilistic {PCA} Self-Organizing Maps},
     journal = {{IEEE} Trans. Neural Networks},
     volume = {20},
     number = {9},
     pages = {1474–1489},
     year = {2009},
     url = {https://doi.org/10.1109/TNN.2009.2025888},
     doi = {10.1109/TNN.2009.2025888},
     timestamp = {Wed, 14 Nov 2018 10:32:52 +0100},
     biburl = {https://dblp.org/rec/journals/tnn/Lopez-RubioOL09.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
}