随机神经网络发展现状综述  

Survey of current progress in random neural network

作　　者：丛爽[1] 王怡雯[1] 

机构地区：[1]中国科学技术大学自动化系,安徽合肥230027

出　　处：《控制理论与应用》2004年第6期975-980,985,共7页Control Theory & Applications

基　　金：安徽省自然科学基金项目 (0 3 0 42 3 0 1)

摘　　要：随机神经网络 (RNN)在人工神经网络中是一类比较独特、出现较晚的神经网络 ,它的网络结构、学习算法、状态更新规则以及应用等方面都因此具有自身的特点 .作为仿生神经元数学模型 ,随机神经网络在联想记忆、图像处理、组合优化问题上都显示出较强的优势 .在阐述随机神经网络发展现状、网络特性以及广泛应用的同时 ,专门将RNN分别与Hopfield网络、模拟退火算法和Boltzmann机在组合优化问题上的应用进行了分析对比 ,指出RNN是解决旅行商 (TSP)Random neural network (RNN) is a special kind of artificial neural network,which is developed recently and has its own peculiarities on the structure,the learning algorithm,the state-updating rule and the applications.As a biological neural mathematical model,RNN has particular advantages of associative memory,image processing and combinatorial optimization.The current progress,the characteristics and the broad applications are elaborated in this paper.The applications on the combinatorial optimization problems solved by different networks such as Hopfield network,simulated annealing algorithm,Boltzmann machine and RNN are analyzed and contrasted.RNN is pointed out to be an effective approach to travelling saleman problem (TSP).

关 键 词：随机神经网络(RNN) HOPFIELD网络 模拟退火算法 BOLTZMANN机 组合优化问题 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]