中文摘要：

提出一种用基因表达式编程（gene expression programming，GEP）自动设计神经网络结构和权值的算法。论述算法的基本思想和基本操作，针对算法的早熟现象和变异率低问题进行了相应的改进，给出这种算法的应用实例。实验结果表明，GEP可以自动设计神经网络的结构，并能给出优化的网络权值，与其他优化算法相比，收敛速度更快。

英文摘要：

An algorithm for automatic designation of the architecture and the weights of neural networks using gene expression programming （GEP） was presented. The fundamental ideas and procedures of the algorithm were discussed. The algorithm was improved to solve the problems of prematurity and lower variance rate. An application for neural networks designation was given. The experimental results indicate that the proposed GEP approach may evolve the architecture of neural network, and can obtain the weights more precisely. Compared to other conventional evolutional algorithms, GEP shows faster convergence.