Convergence analysis of a GA-ICA algorithm

Authors:
J. M. Górriz;C. G. Puntonet;F. Rojas;E. G. Medialdea
Affiliations:
Facultad de Ciencias, Universidad de Granada, Granada, Spain;Facultad de Ciencias, Universidad de Granada, Granada, Spain;Facultad de Ciencias, Universidad de Granada, Granada, Spain;Facultad de Ciencias, Universidad de Granada, Granada, Spain
Venue:
IWINAC'05 Proceedings of the First international work-conference on the Interplay Between Natural and Artificial Computation conference on Artificial Intelligence and Knowledge Engineering Applications: a bioinspired approach - Volume Part II
Year:
2005

Citing 5
Cited 0

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Linear analysis of genetic algorithms

Theoretical Computer Science
Independent component analysis: algorithms and applications

Neural Networks
A new model for time-series forecasting using radial basis functions and exogenous data

Neural Computing and Applications
Nonlinear blind source separation using higher order statistics anda genetic algorithm

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we consider the extension of Genetic-Independent Component Analysis Algorithms (GA-ICA) with guiding operators and prove their convergence to the optimum. This novel method for Blindly Separating unobservable independent component Sources (BSS) consists of novel guiding genetic operators (GGA) and finds the separation matrix which minimizes a contrast function. The convergence is shown under little restrictive conditions for the guiding operator: its effect must disappear in time like the simulated annealing.