Show simple item record

A Connection Between GRBF and MLP

dc.date.accessioned2004-10-04T15:31:32Z
dc.date.accessioned2018-11-24T10:15:04Z
dc.date.available2004-10-04T15:31:32Z
dc.date.available2018-11-24T10:15:04Z
dc.date.issued1992-04-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6566
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/6566
dc.description.abstractBoth multilayer perceptrons (MLP) and Generalized Radial Basis Functions (GRBF) have good approximation properties, theoretically and experimentally. Are they related? The main point of this paper is to show that for normalized inputs, multilayer perceptron networks are radial function networks (albeit with a non-standard radial function). This provides an interpretation of the weights w as centers t of the radial function network, and therefore as equivalent to templates. This insight may be useful for practical applications, including better initialization procedures for MLP. In the remainder of the paper, we discuss the relation between the radial functions that correspond to the sigmoid for normalized inputs and well-behaved radial basis functions, such as the Gaussian. In particular, we observe that the radial function associated with the sigmoid is an activation function that is good approximation to Gaussian basis functions for a range of values of the bias parameter. The implication is that a MLP network can always simulate a Gaussian GRBF network (with the same number of units but less parameters); the converse is true only for certain values of the bias parameter. Numerical experiments indicate that this constraint is not always satisfied in practice by MLP networks trained with backpropagation. Multiscale GRBF networks, on the other hand, can approximate MLP networks with a similar number of parameters.en_US
dc.format.extent3487391 bytes
dc.format.extent2801086 bytes
dc.language.isoen_US
dc.titleA Connection Between GRBF and MLPen_US


Files in this item

FilesSizeFormatView
AIM-1291.pdf2.801Mbapplication/pdfView/Open
AIM-1291.ps3.487Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record