Fast and robust fixed-point algorithms for independent component analysis - PubMed (original) (raw)
Fast and robust fixed-point algorithms for independent component analysis
A Hyvärinen. IEEE Trans Neural Netw. 1999.
Abstract
Independent component analysis (ICA) is a statistical method for transforming an observed multidimensional random vector into components that are statistically as independent from each other as possible. In this paper, we use a combination of two different approaches for linear ICA: Comon's information-theoretic approach and the projection pursuit approach. Using maximum entropy approximations of differential entropy, we introduce a family of new contrast (objective) functions for ICA. These contrast functions enable both the estimation of the whole decomposition by minimizing mutual information, and estimation of individual independent components as projection pursuit directions. The statistical properties of the estimators based on such contrast functions are analyzed under the assumption of the linear mixture model, and it is shown how to choose contrast functions that are robust and/or of minimum variance. Finally, we introduce simple fixed-point algorithms for practical optimization of the contrast functions. These algorithms optimize the contrast functions very fast and reliably.
Similar articles
- Minimax mutual information approach for independent component analysis.
Erdogmus D, Hild KE 2nd, Rao YN, Príncipe JC. Erdogmus D, et al. Neural Comput. 2004 Jun;16(6):1235-52. doi: 10.1162/089976604773717595. Neural Comput. 2004. PMID: 15130248 - A fast fixed-point algorithm for independent component analysis of complex valued signals.
Bingham E, Hyvärinen A. Bingham E, et al. Int J Neural Syst. 2000 Feb;10(1):1-8. doi: 10.1142/S0129065700000028. Int J Neural Syst. 2000. PMID: 10798706 - Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, Kurtosis, and wavelet-ICA.
Mahajan R, Morshed BI. Mahajan R, et al. IEEE J Biomed Health Inform. 2015 Jan;19(1):158-65. doi: 10.1109/JBHI.2014.2333010. Epub 2014 Jun 25. IEEE J Biomed Health Inform. 2015. PMID: 24968340 - Estimating mutual information.
Kraskov A, Stögbauer H, Grassberger P. Kraskov A, et al. Phys Rev E Stat Nonlin Soft Matter Phys. 2004 Jun;69(6 Pt 2):066138. doi: 10.1103/PhysRevE.69.066138. Epub 2004 Jun 23. Phys Rev E Stat Nonlin Soft Matter Phys. 2004. PMID: 15244698 - [Independent Components Analysis (ICA) in the study of electroencephalographic signals].
Urrestarazu E, Iriarte J. Urrestarazu E, et al. Neurologia. 2005 Jul-Aug;20(6):299-310. Neurologia. 2005. PMID: 16007513 Review. Spanish.
Cited by
- Predictive learning shapes the representational geometry of the human brain.
Greco A, Moser J, Preissl H, Siegel M. Greco A, et al. Nat Commun. 2024 Nov 8;15(1):9670. doi: 10.1038/s41467-024-54032-4. Nat Commun. 2024. PMID: 39516221 Free PMC article. - Functional PET/MRI reveals active inhibition of neuronal activity during optogenetic activation of the nigrostriatal pathway.
Haas S, Bravo F, Ionescu TM, Gonzalez-Menendez I, Quintanilla-Martinez L, Dunkel G, Kuebler L, Hahn A, Lanzenberger R, Weigelin B, Reischl G, Pichler BJ, Herfert K. Haas S, et al. Sci Adv. 2024 Oct 25;10(43):eadn2776. doi: 10.1126/sciadv.adn2776. Epub 2024 Oct 25. Sci Adv. 2024. PMID: 39454014 Free PMC article. - iModulonMiner and PyModulon: Software for unsupervised mining of gene expression compendia.
Sastry AV, Yuan Y, Poudel S, Rychel K, Yoo R, Lamoureux CR, Li G, Burrows JT, Chauhan S, Haiman ZB, Al Bulushi T, Seif Y, Palsson BO, Zielinski DC. Sastry AV, et al. PLoS Comput Biol. 2024 Oct 23;20(10):e1012546. doi: 10.1371/journal.pcbi.1012546. eCollection 2024 Oct. PLoS Comput Biol. 2024. PMID: 39441835 Free PMC article. - Compensation versus deterioration across functional networks in amnestic mild cognitive impairment subtypes.
Varela-López B, Zurrón M, Lindín M, Díaz F, Galdo-Alvarez S. Varela-López B, et al. Geroscience. 2024 Oct 5. doi: 10.1007/s11357-024-01369-9. Online ahead of print. Geroscience. 2024. PMID: 39367933 - Neural correlates of motor learning: Network communication versus local oscillations.
Mottaz A, Savic B, Allaman L, Guggisberg AG. Mottaz A, et al. Netw Neurosci. 2024 Oct 1;8(3):714-733. doi: 10.1162/netn_a_00374. eCollection 2024. Netw Neurosci. 2024. PMID: 39355447 Free PMC article.
LinkOut - more resources
Full Text Sources
Other Literature Sources
Miscellaneous