ICA over finite fields-Separability and algorithms

Authors:
Harold W. Gutch;Peter Gruber;Arie Yeredor;Fabian J. Theis
Affiliations:
Max-Planck-Institute for Dynamics and Self-Organization, Department of Nonlinear Dynamics, 37077 Göttingen, Germany and Technical University Munich, Department of Mathematics, 85748 Garching, ...;University of Regensburg, Computational Intelligence and Machine Learning Group, 93040 Regensburg, Germany;Department of Electrical Engineering - Systems, Tel-Aviv University, Tel-Aviv, Israel;Technical University Munich, Department of Mathematics, 85748 Garching, Germany and Institute of Bioinformatics and Systems Biology, Helmholtz Zentrum München, 85764 Neuherberg, Germany
Venue:
Signal Processing
Year:
2012

Citing 13
Cited 2

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Adaptive blind separation of independent sources: a deflation approach

Signal Processing
Factorizing multivariate function classes

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Blind source separation via the second characteristic function

Signal Processing
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
A new concept for separability problems in blind source separation

Neural Computation
Robust Signal Processing for Wireless Communications No. 2

Robust Signal Processing for Wireless Communications No. 2
ICA in Boolean XOR mixtures

ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
ICA over finite fields

LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
An analytical constant modulus algorithm

IEEE Transactions on Signal Processing
Complex random vectors and ICA models: identifiability, uniqueness, and separability

IEEE Transactions on Information Theory
Independent Component Analysis Over Galois Fields of Prime Order

IEEE Transactions on Information Theory
Binary Independent Component Analysis With or Mixtures

IEEE Transactions on Signal Processing

Fast communication: The modified MEXICO for ICA over finite fields

Signal Processing
A Michigan-like immune-inspired framework for performing independent component analysis over Galois fields of prime order

Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

We transfer the ICA model to the case where the underlying field is not the set of reals but an arbitrary finite field. We give conditions for separability of the model, pointing out existing parallels to the real case. Three algorithms capable of solving the task are suggested and we demonstrate their viability through simulations and a possible application of the model.