新型进化神经网络模型

目前的进化神经网络模型大多采用遗传算法进行网络进化设计.而研究表明,这种进化神经网络存在遗传编码、遗传操作及网络结构限制等很多问题;而采用进化规划是一种很好的途径.鉴于此,为了克服传统进化规划算法的不足,结合作者提出的快速免疫进化规划提出了一种网络连接权值及其拓扑结构同时进化优化的新型进化神经网络模型.最后,通过典型的异或分类问题(XOR)比较了该模型同BP神经网络及传统进化神经网络的计算性能,发现它不但计算精度好,而且计算效率高. 

New evolutionary neural networks

Nowadays, the genetic algorithm is a main evolutionary algorithm in evolutionary neural network study. But the previous researches show that, this kind of evolutionary neural network model have many shortcomings, such as genetic code problem, genetic operation problem and restriction on structure of neural network, %et al%. And the evolutionary programming is a good method. To overcome the shortcomings of traditional evolutionary programming, combining the immunized evolutionary programming proposed by author and BP neural network, a new evolutionary neural network model whose architecture and connection weights evolve simultaneously was proposed. Through the typical XOR problem, the new model was compared and analyzed with BP neural network and traditional evolutionary neural network. The computing results show that the precision and efficiency of the new model are all good.