一阶微分方程组边值问题的神经网络解法  

A NEURAL NETWORK SOLUTION TO THE FIRST ORDER DIFFERENTIAL EQUATIONS

作　　者：刘延年[1] 忻欣[1] 

机构地区：[1]东南大学自动化所,南京210018

出　　处：《模式识别与人工智能》1997年第4期305-309,共5页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金

摘　　要：本文利用多层前向神经网络的函数逼近能力,推导出一阶微分方程组边值问题的神经网络解法,为一阶微分方程组的近似解析解的求取提供了便于工程应用的新方法.Based on the theory that a hidden multi-feedforward neural network can approximate a square integral function with an arbitrary accuracy, a method to solve the first order diiferential equations using neural networks is proposed. The approximated solution to the first order differential equations can be achieved which is useful for practical applications.

关 键 词：微分方程 边值问题 神经网络 数值解法 

分 类 号：O175.8[理学—数学] TP18[理学—基础数学]