Incorporating Choas into the Hopfield Neural Network for Combinatorial Optimisation
Incorporating Choas into the Hopfield Neural Network for Combinatorial Optimisation
复制标题
将 Choas 纳入 Hopfield 神经网络进行组合优化
DOI：
--
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
Lipo Wang
中科院分区：
文献类型：
--
作者：
T. Kwok;K. Smith;Lipo Wang
近年来，人们提出了将混沌整合到人工神经网络中的各种方法，并成功地用于解决组合优化问题。本文研究了三种方法：1)Chen & Aihara的具有逐渐衰减的负自耦合项的混沌模拟退火的瞬态混沌神经网络；2) Wang & Smith的混沌模拟退火，采用逐渐减小的时间步长；3) Hayakawa等人在Hopfield网络中加入混沌噪声的方法。N-Queen问题作为一个应用程序来测试和比较这三种方法的性能和鲁棒性。为了对比各种方法的有效性，还包括传统的模拟退火进行比较。
Various approaches of incorporating chaos into artificial neural networks have recently been proposed, and used successfully to solve combinatorial optimisation problems. This paper investigates three such approaches: 1) Chen & Aihara's transiently chaotic neural network with chaotic simulated annealing, which has a gradually decaying negative selfcoupling term; 2) Wang & Smith's chaotic simulated annealing, which employs a gradually decreasing time-step; 3) Hayakawa et al's method of adding chaotic noise to a Hopfield network. The N-Queen problem is used as an application to test and compare the performance and robustness of the three methods. The traditional simulated annealing is also included for comparison in order to contrast the effectiveness of the various approaches.