Associative Neural Network Models Based on a Measure of Manhattan Length

Hiroshi UEDA; Yoichiro ANZAI; Masaya OHTA; Shojiro YONEDA; Akio OGIHARA

Associative Neural Network Models Based on a Measure of Manhattan Length

Hiroshi UEDA, Yoichiro ANZAI, Masaya OHTA, Shojiro YONEDA, Akio OGIHARA

Full Text Views

0

Share
Cite this

Summary :

In this paper, two models for associative memory based on a measure of manhattan length are proposed. First, we propose the two-layered model which has an advantage to its implementation by using PDN. We also refer to the way to improve the recalling ability of this model against noisy input patterns. Secondly, we propose the other model which always recalls the nearest memory pattern in a measure of manhattan length by lateral inhibition. Even if a noise of input pattern is so large that the first model can not recall, this model can recall correctly against such a noisy pattern. We also confirm the performance of the two models by computer simulations.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.3 pp.277-283

Publication Date: 1993/03/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on the 5th Karuizawa Workshop on Circuits and Systems)

Category

Cite this

Copy

Hiroshi UEDA, Yoichiro ANZAI, Masaya OHTA, Shojiro YONEDA, Akio OGIHARA, "Associative Neural Network Models Based on a Measure of Manhattan Length" in IEICE TRANSACTIONS on Fundamentals, vol. E76-A, no. 3, pp. 277-283, March 1993, doi: .
Abstract: In this paper, two models for associative memory based on a measure of manhattan length are proposed. First, we propose the two-layered model which has an advantage to its implementation by using PDN. We also refer to the way to improve the recalling ability of this model against noisy input patterns. Secondly, we propose the other model which always recalls the nearest memory pattern in a measure of manhattan length by lateral inhibition. Even if a noise of input pattern is so large that the first model can not recall, this model can recall correctly against such a noisy pattern. We also confirm the performance of the two models by computer simulations.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e76-a_3_277/_p

Copy

@ARTICLE{e76-a_3_277,
author={Hiroshi UEDA, Yoichiro ANZAI, Masaya OHTA, Shojiro YONEDA, Akio OGIHARA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Associative Neural Network Models Based on a Measure of Manhattan Length},
year={1993},
volume={E76-A},
number={3},
pages={277-283},
abstract={In this paper, two models for associative memory based on a measure of manhattan length are proposed. First, we propose the two-layered model which has an advantage to its implementation by using PDN. We also refer to the way to improve the recalling ability of this model against noisy input patterns. Secondly, we propose the other model which always recalls the nearest memory pattern in a measure of manhattan length by lateral inhibition. Even if a noise of input pattern is so large that the first model can not recall, this model can recall correctly against such a noisy pattern. We also confirm the performance of the two models by computer simulations.},
keywords={},
doi={},
ISSN={},
month={March},}

Copy

TY - JOUR
TI - Associative Neural Network Models Based on a Measure of Manhattan Length
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 277
EP - 283
AU - Hiroshi UEDA
AU - Yoichiro ANZAI
AU - Masaya OHTA
AU - Shojiro YONEDA
AU - Akio OGIHARA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 1993
AB - In this paper, two models for associative memory based on a measure of manhattan length are proposed. First, we propose the two-layered model which has an advantage to its implementation by using PDN. We also refer to the way to improve the recalling ability of this model against noisy input patterns. Secondly, we propose the other model which always recalls the nearest memory pattern in a measure of manhattan length by lateral inhibition. Even if a noise of input pattern is so large that the first model can not recall, this model can recall correctly against such a noisy pattern. We also confirm the performance of the two models by computer simulations.
ER -