层次泛函网络整体学习算法

Universal Learning Algorithm of Hierarchical Function Networks

文中设计了一类单输入单输出泛函网络与双输入单输出泛函网络作为构造层次泛函网络基本模型,提出了一种层次泛函网络模型,给出了层次泛函网络构造方法和整体学习算法,而层次泛函网络的参数利用解方程组来进行逐层学习.以非线性代数方程组为例,指出人们熟知的一些数学解题方法可以用层次泛函网络来表达,探讨了基于层次泛函网络求解非线性代数方程组学习算法实现的一些技术问题.相对传统方法,层次泛函网络更适合于具有层次结构的应用领域.计算机仿真结果表明,这种层次学习方法具有较快的收敛速度和良好的逼近性能.

In this paper, a kind of function networks with single input and single output and function network with double inputs and single output as basis functional network model is designed, and a new hierarchical functional network is presented. The universal learning algorithm and construction method hierarchical function networks is given. Finally, a typical example of application declared that the hierarchical function networks can be regarded as a kind of visualization means of some mathematical methods, based on hierarchical function network for solving nonlinear algebraic equation system, researches are made in some technical problems for realizing algorithm. The results show that hierarchical functional network is very suitable for application domains with hierarchical structures. The simulation results demonstrate that the identification method presented in the paper has rapid convergence speed and powerful performance.