Abstract
In this paper a new method for analyzing Kohonen's self-organizing feature maps is presented. The method makes use of a system of energy functions, one energy function for each processing unit. It is shown that the training process is equivalent to minimizing each energy function subject to constraints. The analysis is used to prove the formation of topologically correct maps when the inherent dimensionality of the input patterns matches that of the network. The energy equations can be used to compute the steady-state weight values of the network. In addition, the analysis allows bounds on the training parameters to be determined. Finally, examples of energy landscapes are presented to graphically show the behavior of the network.
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.
