摘要
根据 BP网络的拓扑特征 ,本文设计了基于结构式二进制编码的遗传算法。在该算法中 ,通过先将庞大的解空间进行分解处理 ,再将分解后的子空间视为个体进行遗传操作 ,能借助遗传算法的优势在全局范围内搜索到最优解所在的子空间 ,从而为下一步应用BP算法进行局部搜索明确了起点、缩小了范围 ,有效解决了 BP算法易陷入局部极小、收敛速度慢甚至不收敛等问题。最后 。
According to the topological characteristics of BP networks, a Genetic Algorithm based on the structural formula binary-coding has been designed in this paper. By means of fractionalizing the large-scale solution-space and performing the GA operations to the fractionalized subspaces, the GA's global-convergence and parallelism can be utilized to search the subspace for the optimal solution in the whole solution-space, thus definitude the starting point and narrow the domain for the next BP's local-search. Testing shows that the two-step algorithm (GA-BP) can solve the existed problems in the NN's training such as local minimum, tardy convergence and so on.
出处
《重庆建筑大学学报》
CSCD
2001年第4期104-109,共6页
Journal of Chongqing Jianzhu University
关键词
遗传算法
神经网络
编码
二进制编码
genetic algorithm (GA)
neural network (NN)
coding
optimization
