Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/5312
Author(s): | Nunes, Luís Almeida, Luís B. Langlois, Thibault |
Date: | 11-Jul-2013 |
Title: | Interpolation Networks |
Pages: | 1750-1754 |
Event title: | International Conference on Neural Networks (ICNN96) |
Keywords: | Interpolation Networks Radial Basis Functions initialisation by prototypes Neural Networks |
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. |
Peerreviewed: | Sim |
Access type: | Restricted Access |
Appears in Collections: | CTI-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
InterpolationNetworks_fromIEEE.pdf Restricted Access | 380,27 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.