基于免疫遗传算法的多层前向神经网络设计  

Multilayer feed-forward neural networks based on immune genetic algorithm

作　　者：罗菲[1] 何明一[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710072

出　　处：《计算机应用》2005年第7期1661-1662,1665,共3页journal of Computer Applications

摘　　要：利用一种基于免疫功能的遗传算法,设计多层前向神经网络,用于实现多层前向神经网络结构的确定和权值空间的搜索。仿真实验结果显示该算法具有比遗传算法和动量BP算法更好的全局收敛性和快速学习网络权值的能力。An optimizing method based on immune genetic algorithm was presented for designing multilayer feed-forward neural network. This algorithm could decide the structure of the multilayer feed-forward neural networks and search the proper weight of this network. The simulation experiments show that this algorithm has the better ability of convergent on whole solution space and the capacity of fast learning than genetic algorithm and momentum BP algorithm.

关 键 词：多层前向神经网络 免疫遗传算法 抗体 浓度 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]