Asymptotically stable multi-valued many-to-many associative memory neural network and its application in image retrieval

Title:

Asymptotically stable multi-valued many-to-many associative memory neural network and its application in image retrieval

Creator:

Chen , Lei, Yang , Geng, Zhang, Yingzhou, Wang , Chuandong, and Yang, Zhen

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:7612ac50-daa6-470a-b0dc-ece61ae5e3ce
uuid:7612ac50-daa6-470a-b0dc-ece61ae5e3ce
doi:10.14311/NNW.2013.23.012

Subject:

Artificial neural network, associative memory model, asymptotical stability, similarity metric, and association-based image retrieval

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

As an important artificial neural network, associative memory model can be employed to mimic human thinking and machine intelligence. In this paper, first, a multi-valued many-to-many Gaussian associative memory model (M3GAM) is proposed by introducing the Gaussian unidirectional associative memory model (GUAM) and Gaussian bidirectional associative memory model (GBAM) into Hattori {et al}'s multi-module associative memory model ((MMA)2). Second, the M3GAM's asymptotical stability is proved theoretically in both synchronous and asynchronous update modes, which ensures that the stored patterns become the M3GAM's stable points. Third, by substituting the general similarity metric for the negative squared Euclidean distance in M3GAM, the generalized multi-valued many-to-many Gaussian associative memory model (GM3GAM) is presented, which makes the M3GAM become its special case. Finally, we investigate the M3GAM's application in association-based image retrieval, and the computer simulation results verify the M3GAM's robust performance.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2013 Volume:23 | Number:2

Harvested from:

CDK

Metadata only:

false