摘要
基于牛顿向前插公式的新的高阶联想记忆系统 (NFI AMS) ,可以用来实现任意阶多变量多项式函数的无误差逼近 ,证明了对于任意多变量连续函数均可通过一组与子区域个数相同的学习数据 ,NFI AMS的学习总是以任意精度收敛的。
A new high\|order Associative Memory System based on Newton's Forward Interpolation formula(NFI AMS) used for implementing the error\|free approximation to multi\|variable polynomial functions with arbitrarily given order is proposed. It is proved that the NFI\|AMS learning always converges to given multi\|variable continuous function with arbitrary accuracy on any set of training data.
出处
《北京联合大学学报》
CAS
2000年第4期48-49,共2页
Journal of Beijing Union University
基金
国家自然科学基金!资助项目 (6 94740 15 )
关键词
神经网络
联想记忆系统
学习收敛性
neural network
associative memory system
learning convergence