Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks
Summary :
Associative memories composed of sparsely interconnected neural networks (SINNs) are suitable for analog hardware implementation. However, the sparsely interconnected structure also gives rise to a decrease in the capability of SINNs for associative memories. Although this problem can be solved by increasing the number of interconnections, the hardware cost goes up rapidly. Therefore, we propose associative memories consisting of multilayer perceptrons (MLPs) with 3-valued weights and SINNs. It is expected that such MLPs can be realized at a lower cost than increasing interconnections in SINNs and can give each neuron in SINNs the global information of an input pattern to improve the storage capacity. Finally, it is confirmed by simulations that our proposed associative memories have good performance.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E85-A No.6 pp.1220-1228
- Publication Date
- 2002/06/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Papers Selected from 2001 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2001))
- Category
Authors
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
Takeshi KAMIO, Hisato FUJISAKA, Mititada MORISUE, "Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E85-A, no. 6, pp. 1220-1228, June 2002, doi: .
Abstract: Associative memories composed of sparsely interconnected neural networks (SINNs) are suitable for analog hardware implementation. However, the sparsely interconnected structure also gives rise to a decrease in the capability of SINNs for associative memories. Although this problem can be solved by increasing the number of interconnections, the hardware cost goes up rapidly. Therefore, we propose associative memories consisting of multilayer perceptrons (MLPs) with 3-valued weights and SINNs. It is expected that such MLPs can be realized at a lower cost than increasing interconnections in SINNs and can give each neuron in SINNs the global information of an input pattern to improve the storage capacity. Finally, it is confirmed by simulations that our proposed associative memories have good performance.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e85-a_6_1220/_p
Copy
@ARTICLE{e85-a_6_1220,
author={Takeshi KAMIO, Hisato FUJISAKA, Mititada MORISUE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks},
year={2002},
volume={E85-A},
number={6},
pages={1220-1228},
abstract={Associative memories composed of sparsely interconnected neural networks (SINNs) are suitable for analog hardware implementation. However, the sparsely interconnected structure also gives rise to a decrease in the capability of SINNs for associative memories. Although this problem can be solved by increasing the number of interconnections, the hardware cost goes up rapidly. Therefore, we propose associative memories consisting of multilayer perceptrons (MLPs) with 3-valued weights and SINNs. It is expected that such MLPs can be realized at a lower cost than increasing interconnections in SINNs and can give each neuron in SINNs the global information of an input pattern to improve the storage capacity. Finally, it is confirmed by simulations that our proposed associative memories have good performance.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1220
EP - 1228
AU - Takeshi KAMIO
AU - Hisato FUJISAKA
AU - Mititada MORISUE
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E85-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2002
AB - Associative memories composed of sparsely interconnected neural networks (SINNs) are suitable for analog hardware implementation. However, the sparsely interconnected structure also gives rise to a decrease in the capability of SINNs for associative memories. Although this problem can be solved by increasing the number of interconnections, the hardware cost goes up rapidly. Therefore, we propose associative memories consisting of multilayer perceptrons (MLPs) with 3-valued weights and SINNs. It is expected that such MLPs can be realized at a lower cost than increasing interconnections in SINNs and can give each neuron in SINNs the global information of an input pattern to improve the storage capacity. Finally, it is confirmed by simulations that our proposed associative memories have good performance.
ER -
English
