Complex infomax: convergence and approximation of infomax with complex nonlinearities
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Independent component analysis (ICA) for separating complex-valued sources is needed for convolutive source-separation in the frequency domain, or for performing source separation on complex-valued data, such as functional magnetic resonance imaging data. Previous complex infomax approaches have proposed using bounded (and hence non-analytic) nonlinearities. We propose using an analytic (and hence unbounded) complex nonlinearity for infomax for processing complex-valued sources. We show that using an analytic nonlinearity for processing complex data has a number of advantages. First, when compared to split-complex approaches (i.e., approaches that split the real and imaginary data into separate channels), the shape of the performance surface is improved resulting in better convergence characteristics. Additionally, the computational complexity is significantly reduced, and finally, the presence of cross terms in the Jacobian enables the analytic nonlinearity to approximate a more general class of input distributions.Keywords
This publication has 10 references indexed in Scilit:
- Independent component analysis of fMRI data in the complex domainMagnetic Resonance in Medicine, 2002
- Universal approximation of fully complex feed-forward neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- On complex infomax applied to functional MRI dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A unifying information-theoretic framework for independent component analysisComputers & Mathematics with Applications, 2000
- A Fast Fixed-Point Algorithm for Independent Component Analysis of Complex Valued SignalsInternational Journal of Neural Systems, 2000
- Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian SourcesNeural Computation, 1999
- Blind separation of convolved mixtures in the frequency domainNeurocomputing, 1998
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Proper complex random processes with applications to information theoryIEEE Transactions on Information Theory, 1993
- The complex backpropagation algorithmIEEE Transactions on Signal Processing, 1991