Abstract
A zonal function (ZF) network on the q dimensional sphere Sq is a network of the form x↦∑k=1nakϕ(x⋅xk) where ϕ:[−1,1]→R is the activation function, xk∈Sq are the centers, and ak∈R. While the approximation properties of such networks are well studied in the context of positive definite activation functions, recent interest in deep and shallow networks motivate the study of activation functions of the form ϕ(t)=|t|, which are not positive definite. In this paper, we define an appropriate smoothness class and establish approximation properties of such networks for functions in this class. The centers can be chosen independently of the target function, and the coefficients are linear combinations of the training data. The constructions preserve rotational symmetries.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.