Classification and ICA using maximum likelihood Hebbian learning
Tóm tắt
We investigate an extension of Hebbian learning 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 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.
Từ khóa
#Independent component analysis #Hebbian theory #Principal component analysis #Neurons #Artificial neural networks #Negative feedback #Nonlinear equations #Computational intelligence #Probability density function #Mean square error methodsTài liệu tham khảo
merenyi, 1994, Self-organising ANNs for Planetary Surface Composition Research, J Geophys Res 99, 10847
10.1142/S0129065789000475
oja, 1992, Principal Components Analysis by Homogeneous Neural Networks, part 1, IEICE Transaction on Information and Systems, 366
simola, 1998, A Tutorial on Support Vector Regression, Technical Report NC2-TR-1998·030 NeuroCOLT2 Technical Report Series
tholen, 1994, Asteroid taxonomy from cluster analysis of photometry
10.1016/S0893-6080(05)80107-8
10.1016/0019-1035(85)90133-2
10.1007/978-1-4471-2063-6_41
10.1214/aos/1176346703
fyfe, 2001, e-Insensitive Hebbian learning, Neuro Computing
10.1007/s004220050156
10.1016/0893-6080(94)90060-4
10.1162/089976601300014394
bishop, 1995, Neural Networks for Pattern Recognition
bell, 1988, The 52 colour asteroid survey: Final Results and interpretation, Lunar Planet Sci Conf (abstract) XXIX, 57
macdonald, 1999, Comparison of Kohonen, scale-invariant and GTM self-organising maps for interpretation of spectral data, European Symposium on Artificial Neural Networks (ESANN), 117