DocumentCode :
395172
Title :
Maximum and minimum likelihood Hebbian rules for exploratory projection pursuit
Author :
Corchado, Emilio ; Fyfe, Colin
Author_Institution :
Appl. Computational Intelligence Res. Unit, Paisley Univ., UK
Volume :
1
fYear :
2002
fDate :
18-22 Nov. 2002
Firstpage :
457
Abstract :
We develop an algorithm which identifies a low dimensional basis of high dimensional data in such a way that the interesting structure in the high dimensional data is optimally preserved. We do this by extending a principal component analysis network so that instead of minimising mean squared error, the network minimises other functions of the error between the projections of the data and the original data set. We do this by considering the residuals from the network in a probabilistic perspective and show that the original PCA network is optimal for Gaussian data. We relate the new rules to the statistical method of exploratory projection pursuit and show it working on both real and artificial data.
Keywords :
Hebbian learning; maximum likelihood estimation; minimisation; neural nets; principal component analysis; Gaussian data; exploratory projection pursuit; high dimensional data; low dimensional basis; maximum likelihood Hebbian rules; minimisation; minimum likelihood Hebbian rules; original PCA network; principal component analysis network; statistical method; Artificial neural networks; Computational intelligence; Computer errors; Data compression; Data mining; Humans; Negative feedback; Principal component analysis; Pursuit algorithms; Statistical analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
Type :
conf
DOI :
10.1109/ICONIP.2002.1202212
Filename :
1202212
Link To Document :
بازگشت