| 引用本文: | 丛 爽, 王怡雯.随机神经网络发展现状综述[J].控制理论与应用,2004,21(6):975~980.[点击复制] |
| CONG Shuang, WANG Yi-wen.Survey of current progress in random neural network[J].Control Theory and Technology,2004,21(6):975~980.[点击复制] |
|
| 随机神经网络发展现状综述 |
| Survey of current progress in random neural network |
| 摘要点击 4564 全文点击 4429 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2004.6.028 |
| 2004,21(6):975-980 |
| 中文关键词 随机神经网络(RNN) Hopfield网络 模拟退火算法 Boltzmann机 组合优化问题 |
| 英文关键词 random neural network(RNN) Hopfield network simulated annealing algorithm Boltzmann machine combinatorial optimization |
| 基金项目 安徽省自然科学基金项目 (03042301). |
|
| 中文摘要 |
| 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)等问题的有效途径 |
| 英文摘要 |
| 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). |
|
|
|
|
|