Abstract
Minor component analysis(MCA) by neural network is endowed with a stochastic discrete-time(SDT) weight vector learning algorithm. It is very difficult to study such algorithm directly. Previous theoretical results on the SDT algorithm are based on its deterministic continuous-time(DCT) ODE asymptotic approximation. However, in general, they are not equivalent at all. Since the behavior of the conditional expectation of the weight vector can be studied by the deterministic discrete-time(DDT) algorithm, it is reasonable to study the SDT algorithm by its DDT algorithm indirectly. By studying the DDT algorithms, we can prove that some of previous MCA neural networks are globally convergent if the learning rate is a variable.
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.
