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

• Autorzy: Funabiki N. , Kurokawa T. , Ohta M.
• Języki publikacji: EN

Abstrakty

EN

Combinatorial optimization problems compose an important class of matliematical 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, thieir 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.

Słowa kluczowe

EN

binary neural network; combinatorial optimization; NP-hard; VLSI design; algorithm

PL

algorytm; binarna sieć neuronowa; N-queens problem; optymalizacja kombinatoryczna; problem n-hetmanów; projekt VLSI

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2002
• Tom: Vol. 31, no 2
• Strony: 271--296
• Opis fizyczny: Bibliogr. 34 poz.,Rys., wykr.,

Twórcy

autor

Funabiki N.

autor

Kurokawa T.

autor

Ohta M.