Maximum-Flow Neural Network: A Novel Neural Network for the Maximum Flow Problem
Summary :
In advance of network communication society by the internet, the way how to send data fast with a little loss becomes an important transportation problem. A generalized maximum flow algorithm gives the best solution for the transportation problem that which route is appropriated to exchange data. Therefore, the importance of the maximum flow algorithm is growing more and more. In this paper, we propose a Maximum-Flow Neural Network (MF-NN) in which branch nonlinearity has a saturation characteristic and by which the maximum flow problem can be solved with analog high-speed parallel processing. That is, the proposed neural network for the maximum flow problem can be realized by a nonlinear resistive circuit where each connection weight between nodal neurons has a sigmodal or piece-wise linear function. The parallel hardware of the MF-NN will be easily implemented.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E92-A No.4 pp.945-951
- Publication Date
- 2009/04/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E92.A.945
- Type of Manuscript
- Special Section PAPER (Special Section on Advanced Technologies Emerging Mainly from the 21st Workshop on Circuits and Systems in Karuizawa)
- 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
Masatoshi SATO, Hisashi AOMORI, Mamoru TANAKA, "Maximum-Flow Neural Network: A Novel Neural Network for the Maximum Flow Problem" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 4, pp. 945-951, April 2009, doi: 10.1587/transfun.E92.A.945.
Abstract: In advance of network communication society by the internet, the way how to send data fast with a little loss becomes an important transportation problem. A generalized maximum flow algorithm gives the best solution for the transportation problem that which route is appropriated to exchange data. Therefore, the importance of the maximum flow algorithm is growing more and more. In this paper, we propose a Maximum-Flow Neural Network (MF-NN) in which branch nonlinearity has a saturation characteristic and by which the maximum flow problem can be solved with analog high-speed parallel processing. That is, the proposed neural network for the maximum flow problem can be realized by a nonlinear resistive circuit where each connection weight between nodal neurons has a sigmodal or piece-wise linear function. The parallel hardware of the MF-NN will be easily implemented.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.945/_p
Copy
@ARTICLE{e92-a_4_945,
author={Masatoshi SATO, Hisashi AOMORI, Mamoru TANAKA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Maximum-Flow Neural Network: A Novel Neural Network for the Maximum Flow Problem},
year={2009},
volume={E92-A},
number={4},
pages={945-951},
abstract={In advance of network communication society by the internet, the way how to send data fast with a little loss becomes an important transportation problem. A generalized maximum flow algorithm gives the best solution for the transportation problem that which route is appropriated to exchange data. Therefore, the importance of the maximum flow algorithm is growing more and more. In this paper, we propose a Maximum-Flow Neural Network (MF-NN) in which branch nonlinearity has a saturation characteristic and by which the maximum flow problem can be solved with analog high-speed parallel processing. That is, the proposed neural network for the maximum flow problem can be realized by a nonlinear resistive circuit where each connection weight between nodal neurons has a sigmodal or piece-wise linear function. The parallel hardware of the MF-NN will be easily implemented.},
keywords={},
doi={10.1587/transfun.E92.A.945},
ISSN={1745-1337},
month={April},}
Copy
TY - JOUR
TI - Maximum-Flow Neural Network: A Novel Neural Network for the Maximum Flow Problem
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 945
EP - 951
AU - Masatoshi SATO
AU - Hisashi AOMORI
AU - Mamoru TANAKA
PY - 2009
DO - 10.1587/transfun.E92.A.945
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2009
AB - In advance of network communication society by the internet, the way how to send data fast with a little loss becomes an important transportation problem. A generalized maximum flow algorithm gives the best solution for the transportation problem that which route is appropriated to exchange data. Therefore, the importance of the maximum flow algorithm is growing more and more. In this paper, we propose a Maximum-Flow Neural Network (MF-NN) in which branch nonlinearity has a saturation characteristic and by which the maximum flow problem can be solved with analog high-speed parallel processing. That is, the proposed neural network for the maximum flow problem can be realized by a nonlinear resistive circuit where each connection weight between nodal neurons has a sigmodal or piece-wise linear function. The parallel hardware of the MF-NN will be easily implemented.
ER -
English
