用连续回归神经网络求解泛函极值问题  

A CONTINUOUS TIME RECURRENT NEURAL NETWORK BASED METHOD TO SOLVE FUNCTIONAL MINIMIZATION PROBLEM

作　　者：刘贺平[1] 张兰玲[1] 孙一康[1] 

机构地区：[1]北京科技大学自动化系,北京100083

出　　处：《电子科学学刊》2000年第5期729-734,共6页

摘　　要：针对信息科学和控制理论中经常涉及的一类泛函极值问题,提出基于连续回归神经网络的求解方法。推导了求解泛函的连续BPTT算法,进而对该算法进行改进,得出一种在线学习算法,为并行实现打下了基础。In this paper, the continuous time recurrent neural network is proposed to solve the functional minimization problem, which is often involved in estimation and control. At first, the continuous time BPTT algorithm corresponding to the problem is presented. Then,an on-line algorithm based on the amendments of the BPTT algorithm is discussed. This on-line algorithm paves the way for parallel realization.

关 键 词：泛函极值 连续回归神经网络 BPTT算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]