Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network

Guangchun LUO; Jinsheng REN; Ke QIN

doi:10.1587/transinf.E95.D.2158

Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network

Guangchun LUO, Jinsheng REN, Ke QIN

Full Text Views

0

Cite this

Summary :

A new training algorithm for the chaotic Adachi Neural Network (AdNN) is investigated. The classical training algorithm for the AdNN and it's variants is usually a “one-shot” learning, for example, the Outer Product Rule (OPR) is the most used. Although the OPR is effective for conventional neural networks, its effectiveness and adequateness for Chaotic Neural Networks (CNNs) have not been discussed formally. As a complementary and tentative work in this field, we modified the AdNN's weights by enforcing an unsupervised Hebbian rule. Experimental analysis shows that the new weighted AdNN yields even stronger dynamical associative memory and pattern recognition phenomena for different settings than the primitive AdNN.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.8 pp.2158-2162

Publication Date: 2012/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.2158

Type of Manuscript: LETTER

Category: Biocybernetics, Neurocomputing

Cite this

Copy

Guangchun LUO, Jinsheng REN, Ke QIN, "Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 8, pp. 2158-2162, August 2012, doi: 10.1587/transinf.E95.D.2158.
Abstract: A new training algorithm for the chaotic Adachi Neural Network (AdNN) is investigated. The classical training algorithm for the AdNN and it's variants is usually a “one-shot” learning, for example, the Outer Product Rule (OPR) is the most used. Although the OPR is effective for conventional neural networks, its effectiveness and adequateness for Chaotic Neural Networks (CNNs) have not been discussed formally. As a complementary and tentative work in this field, we modified the AdNN's weights by enforcing an unsupervised Hebbian rule. Experimental analysis shows that the new weighted AdNN yields even stronger dynamical associative memory and pattern recognition phenomena for different settings than the primitive AdNN.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2158/_p

Copy

@ARTICLE{e95-d_8_2158,
author={Guangchun LUO, Jinsheng REN, Ke QIN, },
journal={IEICE TRANSACTIONS on Information},
title={Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network},
year={2012},
volume={E95-D},
number={8},
pages={2158-2162},
abstract={A new training algorithm for the chaotic Adachi Neural Network (AdNN) is investigated. The classical training algorithm for the AdNN and it's variants is usually a “one-shot” learning, for example, the Outer Product Rule (OPR) is the most used. Although the OPR is effective for conventional neural networks, its effectiveness and adequateness for Chaotic Neural Networks (CNNs) have not been discussed formally. As a complementary and tentative work in this field, we modified the AdNN's weights by enforcing an unsupervised Hebbian rule. Experimental analysis shows that the new weighted AdNN yields even stronger dynamical associative memory and pattern recognition phenomena for different settings than the primitive AdNN.},
keywords={},
doi={10.1587/transinf.E95.D.2158},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 2158
EP - 2162
AU - Guangchun LUO
AU - Jinsheng REN
AU - Ke QIN
PY - 2012
DO - 10.1587/transinf.E95.D.2158
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2012
AB - A new training algorithm for the chaotic Adachi Neural Network (AdNN) is investigated. The classical training algorithm for the AdNN and it's variants is usually a “one-shot” learning, for example, the Outer Product Rule (OPR) is the most used. Although the OPR is effective for conventional neural networks, its effectiveness and adequateness for Chaotic Neural Networks (CNNs) have not been discussed formally. As a complementary and tentative work in this field, we modified the AdNN's weights by enforcing an unsupervised Hebbian rule. Experimental analysis shows that the new weighted AdNN yields even stronger dynamical associative memory and pattern recognition phenomena for different settings than the primitive AdNN.
ER -