The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La procédure de synthèse conventionnelle de réseaux neuronaux discrets et peu interconnectés (DTSINN) pour les mémoires associatives peut générer les cellules avec uniquement une auto-rétroaction en raison de la structure peu interconnectée. Bien que ce problème soit résolu en augmentant le nombre d’interconnexions, la mise en œuvre matérielle devient très difficile. Dans cette lettre, nous proposons le système DTSINN qui stocke les transformées de Walsh discrètes (DWT) bidimensionnelles des modèles de mémoire. Comme chaque élément de DWT implique les informations d'un échantillon entier de données, notre système peut associer les modèles de mémoire souhaités, ce que le DTSINN conventionnel ne parvient pas à faire.
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.
Copier
Takeshi KAMIO, Hideki ASAI, "Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 3, pp. 495-499, March 1999, doi: .
Abstract: The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns, which the conventional DTSINN fails to do.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_3_495/_p
Copier
@ARTICLE{e82-a_3_495,
author={Takeshi KAMIO, Hideki ASAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform},
year={1999},
volume={E82-A},
number={3},
pages={495-499},
abstract={The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns, which the conventional DTSINN fails to do.},
keywords={},
doi={},
ISSN={},
month={March},}
Copier
TY - JOUR
TI - Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 495
EP - 499
AU - Takeshi KAMIO
AU - Hideki ASAI
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 1999
AB - The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns, which the conventional DTSINN fails to do.
ER -