神经网络模型的结构和算法的分离  

Separation of Structure and Algorithm in NN Simulating

作　　者：于敏学[1] 李敏生[1] 

机构地区：[1]北京理工大学计算机科学与工程系,北京100081

出　　处：《北京理工大学学报》2001年第5期587-590,共4页Transactions of Beijing Institute of Technology

基　　金：部级预研项目

摘　　要：研究神经网络模型的结构和算法的分离与结合理论及结合神经网络结构描述语言实现底层代码的重用 .通过对多种神经网络的比较 ,总结出规律 ,论证了结构和算法分离的可行性 ,给出了分离的理想界线和各部分的适当描述方式及合成的具体方法 .只要用户输入对新结构的描述 ,选择算法库中一种合适的算法就能通过软件自动生成神经网络程序 .目前采取这种结构和算法相分离的方式 。The separation of structure and algorithm in NN simulating model and how to reuse the code of NN through language description are introduced. Through comparing meny kinds of neural networks, the rules for NN to follow are concluded the feasibility of separating the structure and the algorithm is demonstrated, and the ideal boundary of the separation and the method of appropriate description and combination of these two parts are given. Users need only give the description of the new structure designed, then select an appropriate one in the algorithm library, and a neural network program will be generated automatically. Up to now, such a method of separating structure and algorithm is considered having advantage and significance.

关 键 词：神经网络模型 结构 算法 分离 代码重用 神经网络程序 理想界线 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]