A novel episodic associative memory model for enhanced classification accuracy


Autoria(s): Wickramasinghe, L.; Alahakoon, D.; Smith-Miles, Kate
Data(s)

15/07/2007

Resumo

A novel approach to Episodic Associative Memory (EAM), known as Episodic Associative Memory with a Neighborhood Effect (EAMwNE) is presented in this paper. It overcomes the representation limitations of existing episodic memory models and increases the potential for their use in practical application.<br />

Identificador

http://hdl.handle.net/10536/DRO/DU:30007653

Idioma(s)

eng

Publicador

Elsevier BV

Relação

http://dro.deakin.edu.au/eserv/DU:30007653/smithmiles-anovel-2007.pdf

http://dx.doi.org/10.1016/j.patrec.2007.02.012

Direitos

2007, Elsevier B.V.

Palavras-Chave #cognitive models #associative memory #single pass learning #online learning
Tipo

Journal Article