TY - GEN
T1 - Algorithms for independent components analysis and higher order statistics
AU - Lee, Daniel D.
AU - Rokni, Uri
AU - Sompolinsky, Haim
PY - 2000
Y1 - 2000
N2 - A latent variable generative model with finite noise is used to decribe several different algorithms for Independent Components Analysis (ICA). In particular, the Fixed Point ICA algorithm is shown to be equivalent to the Expectation-Maximization algorithm for maximum likelihood under certain constraints, allowing the conditions for global convergence to be elucidated. The algorithms can also be explained by their generic behavior near a singular point where the size of the optimal generative bases vanishes. An expansion of the likelihood about this singular point indicates the role of higher order correlations in determining the features discovered by ICA. The application and convergence of these algorithms are demonstrated on a simple illustrative example.
AB - A latent variable generative model with finite noise is used to decribe several different algorithms for Independent Components Analysis (ICA). In particular, the Fixed Point ICA algorithm is shown to be equivalent to the Expectation-Maximization algorithm for maximum likelihood under certain constraints, allowing the conditions for global convergence to be elucidated. The algorithms can also be explained by their generic behavior near a singular point where the size of the optimal generative bases vanishes. An expansion of the likelihood about this singular point indicates the role of higher order correlations in determining the features discovered by ICA. The application and convergence of these algorithms are demonstrated on a simple illustrative example.
UR - http://www.scopus.com/inward/record.url?scp=0005590180&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:0005590180
SN - 0262194503
SN - 9780262194501
T3 - Advances in Neural Information Processing Systems
SP - 491
EP - 497
BT - Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999
PB - Neural information processing systems foundation
T2 - 13th Annual Neural Information Processing Systems Conference, NIPS 1999
Y2 - 29 November 1999 through 4 December 1999
ER -