会議名: 第15回バイオメディカル・ファジィ・システム学会
回次: 15
開催地: 下関
開催日: 2002/10/19 - 2002/10/20
p. 59-60
We have proposed a neural network called LPPH for the SAT. The LPPH can find the global optimum (the solution of SAT) effectively. We have know that the CPU time is greatly depended by the value of the attenuation coefficient α. In this paper, We propose two methods which the LPPH more effective by change the value of α dynamically.