Abstract
This chapter focuses on self-organising neural networks with linear and non-linear activation functions. Many researchers have studied the properties of linear networks and their ability to extract or transfer information regarding the statistics of the observed data. The natural progression to non-linear networks requires alternative analysis tools due to their additional complexity. The emergent behaviour of non-linear networks is much richer than their linear counterparts. A brief review of linear and non-linear self-organising networks within the context of source separation is presented here.KeywordsIndependent Component AnalysisSource SeparationBlind Source SeparationHebbian LearningPrincipal Component Analysis AlgorithmThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
