### Abstract

Combinatorial optimization problems compose an important class of mathematical problems that include a variety of practical applications, such as VLSI design automation, communication network design and control, job scheduling, games, and genome informatics. These problems usually have a large number of variables to be solved. For example, problems for VLSI design automation require several million variables. Besides, their computational complexity is often intractable due to NP-hardness. Neural networks have provided elegant solutions as approximation algorithms to these hard problems due to their natural parallelism and their affinity to hardware realization. Particularly, binary neural networks have great potential to conform to current digital VLSI design technology, because any state and parameter in binary neural networks are expressed in a discrete fashion. This paper presents our studies on binary neural networks to the N-queens problem, and the three different approaches to VLSI implementations focusing on the efficient realization of the synaptic connection networks. Reconfigurable devices such as CPLDs and FPGAs contribute the realization of a scalable architecture with the ultra high speed of computation. Based on the proposed architecture, more than several thousands of binary neurons can be realized on one FPGA chip.

Original language | English |
---|---|

Pages (from-to) | 271-296 |

Number of pages | 26 |

Journal | Control and Cybernetics |

Volume | 31 |

Issue number | 2 |

Publication status | Published - 2002 |

### Fingerprint

### Keywords

- Algorithm
- Binary neural network
- Combinatorial optimization
- NP-hard
- VLSI design

### ASJC Scopus subject areas

- Human-Computer Interaction
- Control and Systems Engineering

### Cite this

*Control and Cybernetics*,

*31*(2), 271-296.

**Binary neural networks for N-queens problems and their VLSI implementations.** / Funabiki, Nobuo; Kurokawa, Takakazu; Ohta, Masaya.

Research output: Contribution to journal › Article

*Control and Cybernetics*, vol. 31, no. 2, pp. 271-296.

}

TY - JOUR

T1 - Binary neural networks for N-queens problems and their VLSI implementations

AU - Funabiki, Nobuo

AU - Kurokawa, Takakazu

AU - Ohta, Masaya

PY - 2002

Y1 - 2002

N2 - Combinatorial optimization problems compose an important class of mathematical problems that include a variety of practical applications, such as VLSI design automation, communication network design and control, job scheduling, games, and genome informatics. These problems usually have a large number of variables to be solved. For example, problems for VLSI design automation require several million variables. Besides, their computational complexity is often intractable due to NP-hardness. Neural networks have provided elegant solutions as approximation algorithms to these hard problems due to their natural parallelism and their affinity to hardware realization. Particularly, binary neural networks have great potential to conform to current digital VLSI design technology, because any state and parameter in binary neural networks are expressed in a discrete fashion. This paper presents our studies on binary neural networks to the N-queens problem, and the three different approaches to VLSI implementations focusing on the efficient realization of the synaptic connection networks. Reconfigurable devices such as CPLDs and FPGAs contribute the realization of a scalable architecture with the ultra high speed of computation. Based on the proposed architecture, more than several thousands of binary neurons can be realized on one FPGA chip.

AB - Combinatorial optimization problems compose an important class of mathematical problems that include a variety of practical applications, such as VLSI design automation, communication network design and control, job scheduling, games, and genome informatics. These problems usually have a large number of variables to be solved. For example, problems for VLSI design automation require several million variables. Besides, their computational complexity is often intractable due to NP-hardness. Neural networks have provided elegant solutions as approximation algorithms to these hard problems due to their natural parallelism and their affinity to hardware realization. Particularly, binary neural networks have great potential to conform to current digital VLSI design technology, because any state and parameter in binary neural networks are expressed in a discrete fashion. This paper presents our studies on binary neural networks to the N-queens problem, and the three different approaches to VLSI implementations focusing on the efficient realization of the synaptic connection networks. Reconfigurable devices such as CPLDs and FPGAs contribute the realization of a scalable architecture with the ultra high speed of computation. Based on the proposed architecture, more than several thousands of binary neurons can be realized on one FPGA chip.

KW - Algorithm

KW - Binary neural network

KW - Combinatorial optimization

KW - NP-hard

KW - VLSI design

UR - http://www.scopus.com/inward/record.url?scp=0036914207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036914207&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036914207

VL - 31

SP - 271

EP - 296

JO - Control and Cybernetics

JF - Control and Cybernetics

SN - 0324-8569

IS - 2

ER -