The search functionality is under construction.

The search functionality is under construction.

We apply some variants of evolutionary computations to the fully-connected neural network model of associative memory. Among others, when we regard it as a parameter optimization problem, we notice that the model has some favorable properties as a test function of evolutionary computations. So far, many functions have been proposed for comparative study. However, as Whitley and his colleagues suggested, many of the existing common test functions have some problems in comparing and evaluating evolutionary computations. In this paper, we focus on the possibilities of using the fully-connected neural network model as a test function of evolutionary computations.

- Publication
- IEICE TRANSACTIONS on Information Vol.E82-D No.1 pp.318-325

- Publication Date
- 1999/01/25

- Publicized

- Online ISSN

- DOI

- Type of Manuscript
- PAPER

- Category
- Bio-Cybernetics and Neurocomputing

The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.

Copy

Akira IMADA, Keijiro ARAKI, "Fully-Connected Neural Network Model of Associative Memory as a Test Function of Evolutionary Computations" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 1, pp. 318-325, January 1999, doi: .

Abstract: We apply some variants of evolutionary computations to the fully-connected neural network model of associative memory. Among others, when we regard it as a parameter optimization problem, we notice that the model has some favorable properties as a test function of evolutionary computations. So far, many functions have been proposed for comparative study. However, as Whitley and his colleagues suggested, many of the existing common test functions have some problems in comparing and evaluating evolutionary computations. In this paper, we focus on the possibilities of using the fully-connected neural network model as a test function of evolutionary computations.

URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_1_318/_p

Copy

@ARTICLE{e82-d_1_318,

author={Akira IMADA, Keijiro ARAKI, },

journal={IEICE TRANSACTIONS on Information},

title={Fully-Connected Neural Network Model of Associative Memory as a Test Function of Evolutionary Computations},

year={1999},

volume={E82-D},

number={1},

pages={318-325},

abstract={We apply some variants of evolutionary computations to the fully-connected neural network model of associative memory. Among others, when we regard it as a parameter optimization problem, we notice that the model has some favorable properties as a test function of evolutionary computations. So far, many functions have been proposed for comparative study. However, as Whitley and his colleagues suggested, many of the existing common test functions have some problems in comparing and evaluating evolutionary computations. In this paper, we focus on the possibilities of using the fully-connected neural network model as a test function of evolutionary computations.},

keywords={},

doi={},

ISSN={},

month={January},}

Copy

TY - JOUR

TI - Fully-Connected Neural Network Model of Associative Memory as a Test Function of Evolutionary Computations

T2 - IEICE TRANSACTIONS on Information

SP - 318

EP - 325

AU - Akira IMADA

AU - Keijiro ARAKI

PY - 1999

DO -

JO - IEICE TRANSACTIONS on Information

SN -

VL - E82-D

IS - 1

JA - IEICE TRANSACTIONS on Information

Y1 - January 1999

AB - We apply some variants of evolutionary computations to the fully-connected neural network model of associative memory. Among others, when we regard it as a parameter optimization problem, we notice that the model has some favorable properties as a test function of evolutionary computations. So far, many functions have been proposed for comparative study. However, as Whitley and his colleagues suggested, many of the existing common test functions have some problems in comparing and evaluating evolutionary computations. In this paper, we focus on the possibilities of using the fully-connected neural network model as a test function of evolutionary computations.

ER -