Experimental analysis of chaotic neural network models for combinatorial optimization under a unifying framework
Experimental analysis of chaotic neural network models for combinatorial optimization under a unifying framework
复制标题
DOI：
10.1016/s0893-6080(00)00047-2
复制
发表时间：
2000-09-01
期刊：
影响因子：
7.8
通讯作者：
Smith, KA
中科院分区：
文献类型：
--
作者：
Kwok, T;Smith, KA
本文的目的是研究求解组合优化问题的混沌神经网络模型的理论和实验性质。以前我们已经提出了一个统一的框架，包括三种主要的模型类型，即Chen和Aihara的具有衰减自耦合的混沌模拟退火法(CSA)，Wang和Smith的具有衰减时间步长的CSA，以及具有混沌噪声的Hopfield网络。这些模型中的每一个都可以表示为在一定条件下的框架下的特例。本文将该框架与实验结果相结合，为每个模型的混沌神经动力学效应提供了新的见解。通过计算机仿真求解不同规模的N皇后问题，比较了CNN模型在不同参数空间中的优化性能，并从可行性、效率、稳健性和可扩展性等方面对其进行了衡量。此外，识别了对有效优化至关重要的特征混沌神经动力学，并提供了选择相应模型参数的指南。(C)2000爱思唯尔科学有限公司。保留所有权利。
The aim of this paper is to study both the theoretical and experimental properties of chaotic neural network (CNN) models for solving combinatorial optimization problems. Previously we have proposed a unifying framework which encompasses the three main model types, namely, Chen and Aihara's chaotic simulated annealing (CSA) with decaying self-coupling, Wang and Smith's CSA with decaying timestep, and the Hopfield network with chaotic noise. Each of these models can be represented as a special case under the framework for certain conditions. This paper combines the framework with experimental results to provide new insights into the effect of the chaotic neurodynamics of each model. By solving the N-queen problem of various sizes with computer simulations, the CNN models are compared in different parameter spaces, with optimization performance measured in terms of feasibility, efficiency, robustness and scalability. Furthermore, characteristic chaotic neurodynamics crucial to effective optimization are identified, together with a guide to choosing the corresponding model parameters. (C) 2000 Elsevier Science Ltd. All rights reserved.