Please use this identifier to cite or link to this item:
Almeida, Luís B.
Radial Basis Functions
initialisation by prototypes
|Abstract:||This paper introduces a new type of network based on local response units, the ‘Intelpolation Networh’ (INS).U nder certain conditions this network is an interpolator. Its formulation allows a type of initialisation by prototypes that will set the net in a good initial starting point for the subsequent supervised learning process. These networks can be seen as a type of ‘Radial Basis Functions Network’ (RBFN) [Moody88]. However, their basis functions are essentially inverse squared distances instead of Gaussian functions. A brief description of the origin and motivation of INS is made in the first section, followed by the description of the first experiments with these networks.|
|Appears in Collections:||CTI-CRI - Comunicações a conferências internacionais|
Files in This Item:
|InterpolationNetworks_fromIEEE.pdf||380.27 kB||Adobe PDF||View/Open Request a copy|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.