一种基于混合遗传算法学习的过程神经网络

Procedure neural networks based on being learned by hybrid genetic algorithm

提出了过程神经网络的一种学习算法.利用基函数的正交性,将输入函数和网络权函数表示为同一组正交基的展开形式后,使用遗传算法与BP算法结合的混合遗传算法训练过程神经网络,为简化计算,对权值基函数的选取和离散数据的函数拟合方法进行了调整,减少了误差.并以木材生长密度预测为例,验证了算法的有效性.

A learning algorithm of procedure neural networks is proposed. After this input functions and the network weight functions are represented as expansion of a same orthogonal basis with orthogonality of basis functions, procedure neural networks is learned by hybrid genetic algorithm. In consideration of simplicity of calculation, weight bases function selection and function fitting method for discrete data are adjusted so as to reduce the error. And the availability and effectiveness of the algorithm is proved by forecast of timber growth ring density.