ICA model estimation using an optimized version of genetic algorithms
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Independent Component Analysis (ICA), Blind Source Separation (BSS), Artificial Neural Networks (ANN), Genetic Algorithms (GA)
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: -
Abstract: This paper presents a method of estimating the independent component analysis model based on the use of a training algorithm based on an optimized version of genetic algorithms with a neural network algorithm. The mixed training algorithm is applied to optimize the objective function negentropy used to estimate the ICA model. The proposed estimation algorithm improves the training scheme based on genetic algorithms by using for crossover the most suitable chromosomes evaluated by the objective function with the parameters calculated calculated accordingly by a multilayer neural network algorithm. The performances of the proposed algorithm for estimating the independent components were evaluated through a comparative analysis with the versions of FastICA algorithms based on the standard Newton method, as well as on the secant method of derivation of the training scheme at the level of the optimization stage of the approximate objective function. The experimental results for the proposed algorithm for estimating the independent components are established in specific blind source separation applications using unidimensional and bidimensional signals.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7840
Loading