Complex-Valued Bipartite Auto-Associative Memory
Summary :
Complex-valued Hopfield associative memory (CHAM) is one of the most promising neural network models to deal with multilevel information. CHAM has an inherent property of rotational invariance. Rotational invariance is a factor that reduces a network's robustness to noise, which is a critical problem. Here, we proposed complex-valued bipartite auto-associative memory (CBAAM) to solve this reduction in noise robustness. CBAAM consists of two layers, a visible complex-valued layer and an invisible real-valued layer. The invisible real-valued layer prevents rotational invariance and the resulting reduction in noise robustness. In addition, CBAAM has high parallelism, unlike CHAM. By computer simulations, we show that CBAAM is superior to CHAM in noise robustness. The noise robustness of CHAM decreased as the resolution factor increased. On the other hand, CBAAM provided high noise robustness independent of the resolution factor.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E97-A No.8 pp.1680-1687
- Publication Date
- 2014/08/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E97.A.1680
- Type of Manuscript
- PAPER
- Category
- Nonlinear Problems
Authors
Yozo SUZUKI
University of Yamanashi
Masaki KOBAYASHI
University of Yamanashi
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Yozo SUZUKI, Masaki KOBAYASHI, "Complex-Valued Bipartite Auto-Associative Memory" in IEICE TRANSACTIONS on Fundamentals,
vol. E97-A, no. 8, pp. 1680-1687, August 2014, doi: 10.1587/transfun.E97.A.1680.
Abstract: Complex-valued Hopfield associative memory (CHAM) is one of the most promising neural network models to deal with multilevel information. CHAM has an inherent property of rotational invariance. Rotational invariance is a factor that reduces a network's robustness to noise, which is a critical problem. Here, we proposed complex-valued bipartite auto-associative memory (CBAAM) to solve this reduction in noise robustness. CBAAM consists of two layers, a visible complex-valued layer and an invisible real-valued layer. The invisible real-valued layer prevents rotational invariance and the resulting reduction in noise robustness. In addition, CBAAM has high parallelism, unlike CHAM. By computer simulations, we show that CBAAM is superior to CHAM in noise robustness. The noise robustness of CHAM decreased as the resolution factor increased. On the other hand, CBAAM provided high noise robustness independent of the resolution factor.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E97.A.1680/_p
Copy
@ARTICLE{e97-a_8_1680,
author={Yozo SUZUKI, Masaki KOBAYASHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Complex-Valued Bipartite Auto-Associative Memory},
year={2014},
volume={E97-A},
number={8},
pages={1680-1687},
abstract={Complex-valued Hopfield associative memory (CHAM) is one of the most promising neural network models to deal with multilevel information. CHAM has an inherent property of rotational invariance. Rotational invariance is a factor that reduces a network's robustness to noise, which is a critical problem. Here, we proposed complex-valued bipartite auto-associative memory (CBAAM) to solve this reduction in noise robustness. CBAAM consists of two layers, a visible complex-valued layer and an invisible real-valued layer. The invisible real-valued layer prevents rotational invariance and the resulting reduction in noise robustness. In addition, CBAAM has high parallelism, unlike CHAM. By computer simulations, we show that CBAAM is superior to CHAM in noise robustness. The noise robustness of CHAM decreased as the resolution factor increased. On the other hand, CBAAM provided high noise robustness independent of the resolution factor.},
keywords={},
doi={10.1587/transfun.E97.A.1680},
ISSN={1745-1337},
month={August},}
Copy
TY - JOUR
TI - Complex-Valued Bipartite Auto-Associative Memory
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1680
EP - 1687
AU - Yozo SUZUKI
AU - Masaki KOBAYASHI
PY - 2014
DO - 10.1587/transfun.E97.A.1680
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E97-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2014
AB - Complex-valued Hopfield associative memory (CHAM) is one of the most promising neural network models to deal with multilevel information. CHAM has an inherent property of rotational invariance. Rotational invariance is a factor that reduces a network's robustness to noise, which is a critical problem. Here, we proposed complex-valued bipartite auto-associative memory (CBAAM) to solve this reduction in noise robustness. CBAAM consists of two layers, a visible complex-valued layer and an invisible real-valued layer. The invisible real-valued layer prevents rotational invariance and the resulting reduction in noise robustness. In addition, CBAAM has high parallelism, unlike CHAM. By computer simulations, we show that CBAAM is superior to CHAM in noise robustness. The noise robustness of CHAM decreased as the resolution factor increased. On the other hand, CBAAM provided high noise robustness independent of the resolution factor.
ER -
English
