Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/5312
Autoria: | Nunes, Luís Almeida, Luís B. Langlois, Thibault |
Data: | 11-Jul-2013 |
Título próprio: | Interpolation Networks |
Paginação: | 1750-1754 |
Título do evento: | International Conference on Neural Networks (ICNN96) |
Palavras-chave: | Interpolation Networks Radial Basis Functions initialisation by prototypes Neural Networks |
Resumo: | 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. |
Arbitragem científica: | Sim |
Acesso: | Acesso Restrito |
Aparece nas coleções: | CTI-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
InterpolationNetworks_fromIEEE.pdf Restricted Access | 380,27 kB | Adobe PDF | Ver/Abrir Request a copy |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.