基于动态适应度的基因表达式编程挖掘反函数

Mining inverse function based on gene expression programming with dynamic fitness

为提高基因表达式编程(GEP)发现知识效率,提出并实现了基因表达式编程的动态适应度函数。将逐步权重自适应(SAW)应用于基因表达式编程中适应度函数的动态调整;将线性N维向量函数引入作为适应度函数的组件,用于提高求适应度效率;通过挖掘反函数和方程求解的实验,表明新方法比传统基因表达式编程所求得的反函数表达式的精确度有较大的优势,性能提高约8%。

To improve the efficiency of the GEP discovering knowledge, this paper proposed and implemented the dynamic fitness function of GEP. Applied the precision stepwise adaptation of weights to the dynamic adaptation of the GEP fitness function. Took the linear N dimension vector function as a component of the GEP fitness function, with which improved the computing efficiency. Gave extended experiments on inverse function mining and equation solving to show that the new method improves the precision of the inverse function by around 8% compare to the traditional GEP.