Buscar

 

RI UFLA (Universidade Federal de Lavras) >
Revistas UFLA >
Infocomp >

Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/10278

Title: Evolutionary and Hebbian analysis of hierarchically coupled associative memories
???metadata.dc.creator???: Gomes, Rogério Martins
Borges, Henrique Elias
Keywords: Associative memory
Evolutionary computation
Generalized-brain-state-in-a-box (GBSB) model
Theory of neuronal group selection (TNGS)
Memória associativa
Computação evolutiva
Modelo de rede neural artificial GBSB
Teoria da seleção de grupo neuronal (TAG)
Publisher: Editora da UFLA
???metadata.dc.date???: 1-Jun-2012
Citation: GOMES, R. M.; BORGES, H. E. Evolutionary and Hebbian analysis of hierarchically coupled associative memories. INFOCOMP: Journal of Computer Science, Lavras, v. 11, n. 2, p. 43-55, June 2012.
Abstract: Inspired by The Theory of Neuronal Group Selection (TNGS) we have conducted a comparative storage and retrieval analysis of a multi-level or hierarchically coupled associative memory through evolutionary computation and Hebbian learning. The TNGS establishes that memory processes can be described as being organized, functionally, in hierarchical levels, where higher levels coordinate sets of functions of the lower levels. The most basic units in the cortical area of the brain are formed during epigenesis and are called neuronal groups, which are defined as a set of localized tightly coupled neurons constituting what we call our first-level blocks of memories. On the other hand the higher levels are formed during our lives, or ontogeny, through selective strengthening or weakening of the neural connections amongst the neuronal groups. In this sense, this paper describes and compares a method of acquiring the inter- group synapses for the proposed coupled system using both evolutionary computation and Hebbian learning. The results show that evolutionary computation, more specifically genetic algorithms, is more suitable for network acquisition than Hebbian learning because it allows for the emergence of complex behaviours which a repotentially excluded due to the well known crossover effect constraints presented in Hebbian learning. Simulations have been carried out considering a wide range of the system parameters.
Other Identifiers: http://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/355
???metadata.dc.language???: eng
Appears in Collections:Infocomp

Files in This Item:

There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


View Statistics

 


DSpace Software Copyright © 2002-2010  Duraspace - Feedback