【摘要】 函数型连接神经网络通过对输入模式预先进行非线性扩展,增强了输入信号的模式表达,从而大大简化网络结构,降低计算复杂度。本文提出一种外积扩展型连接神经网络,用于辨识幂函数非线性系统,并与MLP和CFLNN网络对比,仿真结果表明,外积型辨识幂函数非线性系统结构简单、计算量低、性能最优。更多还原

【Abstract】 A functional link neural network can expand its input pattern to eliminate the need of hidden layer without sacrifice its performance. Thus the network structure and the computational complexity can be remarkably reduced. In this paper, a muti- extend- ed link neural network is introduced in identification of power function nonlinear system. It is contrasted with MLP and CFLNN net- work and simulation result indicates that its structure is very simple and its computational complexity is low.更多还原