论文信息 - A New Neural Implementation of Exploratory Projection Pursuit

A New Neural Implementation of Exploratory Projection Pursuit

We investigate an extension of the learning rules in a Principal Component Analysis network which has been derived to be optimal for a specific probability density function(pdf). We note that this probability density function is one of a family of pdfs and investigate the learning rules formed in order to be optimal for several members of this family. We show that, whereas previous authors [5] have viewed the single member of the family as an extension of PCA, it is more appropriate to view the whole family of learning rules as methods of performing Exploratory Projection Pursuit(EPP). We explore the performance of our method first in response to an artificial data type, then to a real data set.

Emilio Corchado | Colin Fyfe | C. Fyfe | E. Corchado

[1] Colin Fyfe,et al. Non-linear data structure extraction using simple hebbian networks , 1995, Biological Cybernetics.

[2] Colin Fyfe. PCA Properties of Interneurons , 1993 .

[3] E. Oja,et al. Principal component analysis by homogeneous neural networks, Part I : The weighted subspace criterion , 1992 .

[4] Juha Karhunen,et al. Representation and separation of signals using nonlinear PCA type learning , 1994, Neural Networks.

[5] Lei Xu,et al. Least mean square error reconstruction principle for self-organizing neural-nets , 1993, Neural Networks.

[6] Aapo Hyvärinen,et al. Complexity Pursuit: Separating Interesting Components from Time Series , 2001, Neural Computation.

[7] Bernhard Schölkopf,et al. A tutorial on support vector regression , 2004, Stat. Comput..

[8] Christopher M. Bishop,et al. Neural networks for pattern recognition , 1995 .

[9] Erkki Oja,et al. Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[10] Colin Fyfe,et al. epsilon-insensitive Hebbian learning , 2002, Neurocomputing.

[11] D. Freedman,et al. Asymptotics of Graphical Projection Pursuit , 1984 .